Open source coding agents that ran on a fresh machine
Agents that write and change code from a prompt, ordered by whether each one installed and started when Argusic tried it fresh, with the recorded session one click away.
Tested between and . Each row shows its own test date; a project can change after that day.
294 of 309 tested projects run. 23 more waiting for a test.
In short: 232 of the 309 tested projects started as-is on a fresh machine: herdr, oh-my-claudecode, ffmpeg-skill, openfilm, TokenEconomizer, marionette, tuios, and ANUS, and 224 more. 62 more started once a stand-in replaced a service they expect, such as a database: rea, claude-context, grok-cli, tdd-guard, DemoGPT, Tianshu-harness, pi-from-scratch, and MiniCode, and 54 more. 15 could not be verified: nWave, harmonyos-ai-skill, fence, agentty, router, Codewhale, agent-orchestrator, and scrawl, and 7 more; the log shows where each one stopped.
Measured by Argusic on a fresh machine every time. Every number links to its evidence.
| # | project | verdict | Argusic Score | language | stars | tested on |
|---|---|---|---|---|---|---|
| 1 | herdr | Runs | 100 / 100 | Rust | 52,314 | |
the runtime your coding agents live on What the test found: herdr 0.8.2 builds, runs its server, passes all Rust unit tests, Python maintenance tests, Bun integration tests, and plugin marketplace tests with no failures. 19 minutes. | ||||||
| 2 | oh-my-claudecode | Runs | 100 / 100 | TypeScript | 41,006 | |
Teams-first Multi-agent orchestration for Claude Code What the test found: Oh-My-ClaudeCode v5.2.0 CLI tool builds and responds to version/help/info commands; 1,094+ tests pass with 3 env-constrained failures (Node 18 engine gap + shallow git). 31 minutes. | ||||||
| 3 | ffmpeg-skill | Runs | 100 / 100 | Python | 9,611 | |
Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions... What the test found: The repo installs via npx ffmpeg-skill, doctor reports 0 required capabilities missing, the MCP server answers initialize with ffmpeg-skill 2.10.3 and tools/list with 12 tools, both full test suites pass on clean output directories (907 + 169 tests, all OK with only skips), and cut/fit/caption/loudness produced files... 72 minutes. | ||||||
| 4 | openfilm | Runs | 100 / 100 | TypeScript | 8,974 | |
The open source AI video agent: turns any coding agent into a video agent, with editors to change anything it makes. What the test found: All three workspace packages install, build, and pass their full test suites (104+18+104 tests); the openfilm CLI renders films to valid MP4 frames using Playwright with a headless Chromium browser. 6 minutes. | ||||||
| 5 | TokenEconomizer | Runs | 100 / 100 | Python | 7,946 | |
Experience-Driven Black-Box Cost Control for Coding Agents What the test found: Package tokeneconomizer installs, its 424 offline tests pass, its CLI reports healthy, and the experiments test suite passes 396 of 397. 1 minute. | ||||||
| 6 | marionette | Runs | 100 / 100 | JavaScript | 7,047 | |
A JavaScript library for structured interfaces, with explicit ownership and lifecycle. Built for agent-led development. Canonical Marionette repository; v4... What the test found: With Node 24.19.0 on PATH, npm install/build/test succeed: 531 packages installed, build exit 0, npm test passed 145 files and 2114 tests, and an ESM-dist probe proved Application start, rendering, and Region dismissal work end to end. 3 minutes. | ||||||
| 7 | tuios | Runs | 100 / 100 | Go | 6,721 | |
A terminal window manager that knows what your agents are doing. Tiling panes, workspaces, sessions that survive restarts, and one Inbox for every coding... What the test found: TUIOS builds from source using the Charm Go compiler v1.26.6 with the pure-Go backend. Both the tuios multiplexer (36MB) and tuios-web web terminal server (46MB) binaries compile successfully. All 50 test suites pass including app, vt, server, session, terminal, and config. The tuios binary launches correctly under a... 23 minutes. | ||||||
| 8 | ANUS | Runs | 100 / 100 | JavaScript | 6,558 | |
A free coding agent in your terminal. It runs on the smartest free model that is up today. What the test found: The ANUS CLI (v0.2.2) builds, its 28 unit tests pass, --version prints 0.2.2, and --help prints all commands and options. 1 minute. | ||||||
| 9 | vibesdk | Runs | 100 / 100 | TypeScript | 5,484 | |
An open-source vibe coding platform that helps you build your own vibe-coding platform, built entirely on Cloudflare stack What the test found: The VibeSDK project installs, builds, typechecks, and passes all 514 unit tests (root vitest + SDK bun tests) using Bun 1.4.2 and Node.js 20.18.0 inside the container. 11 minutes. | ||||||
| 10 | pstack-claude | Runs | 100 / 100 | JavaScript | 4,701 | |
Antigravity, Claude Code, Codex, Copilot, DeepSeek Harness, Gemini, Grok Build, Kimi Code, MiniMax Code, Muse, OMP, OpenCode, Pi, Prime Agent, etc versions of... What the test found: pstack plugin v0.9.45 is installed, enabled, and registered in Codex 0.167.0; the SessionStart hook injects pstack routing; all 54 skill directories are discoverable; the generator, bun test suite (227/227), and vendored scripts (118/118) all pass; codex exec successfully invoked pstack:poteto-mode through the real... 8 minutes. | ||||||
| 11 | twinny | Runs | 100 / 100 | TypeScript | 3,706 | |
Open-source AI coding assistant for VS Code. Coding agent, code completion, chat, edits and reviews with local or hosted models. Your models, your... What the test found: npm install completed, TypeScript compilation and esbuild bundling succeed, the full VS Code extension test suite passes (642 passed, 0 failed), and both twinny-node and twinny-server CLI binaries respond correctly. 8 minutes. | ||||||
| 12 | omnara | Runs | 100 / 100 | Go | 3,435 | |
The open-source managed agent platform. A self-hostable alternative to Claude Managed Agents and OpenAI's Agents API. What the test found: Omnara builds, all 124 unit test packages pass, all 34 integration test packages pass against live PostgreSQL 18 + Redis 7 + MinIO S3, all 4 server binaries build and the API binary starts and responds on port 8080, and the frontend web app builds successfully. 43 minutes. | ||||||
| 13 | git-ai | Runs | 100 / 100 | Rust | 3,006 | |
A Git extension for tracking the AI-generated code in your repos What the test found: git-ai builds from source with cargo, all 2481 unit tests pass, 1310+ sampled integration tests across checkpointing, blame, diff, rewrite ops, agent presets, worktrees, and async daemon mode all pass with RUSTUP_TOOLCHAIN=stable and GIT_AI_TEST_BINARY_PATH set. 45 minutes. | ||||||
| 14 | gentle-shell | Runs | 100 / 100 | TypeScript | 2,886 | |
Gentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory, and permission... What the test found: gentle-pi v3.7.0 builds, installs, its 3903 unit tests pass, provider-contract mirror check passes, runtime-harness passes, the gentle-shell binary launches reporting version 3.7.0 with pi 0.87.1, and the package-local Gentle AI v3.7.0 binary is installed. 29 minutes. | ||||||
| 15 | teaql-agent-kit | Runs | 100 / 100 | TypeScript | 2,822 | |
A model-driven harness for AI coding agents: semantic modeling, app generation, progressive API Assist and evidence-based verification. What the test found: Python-based teaql_workspace.py tool verifies and applies runtime source configurations for all 7 supported languages; the build-teaql-app skill, golden examples, and reference documentation are complete and well-formed; the npx skills add install path is gated by a Node.js 22 requirement not met in this container. 3 minutes. | ||||||
| 16 | pr-lens | Runs | 100 / 100 | TypeScript | 2,433 | |
The fastest way to understand code What the test found: PR Lens monorepo installs, builds, typechecks, and all 868 tests pass on 7 packages (schema, renderer, cli, action, agent-skill, gitlab-component, bitbucket-pipe) with the CLI binary functional at version 0.11.0. 11 minutes. | ||||||
| 17 | claude-code-history-viewer | Runs | 100 / 100 | TypeScript | 2,336 | |
Desktop app and web server to browse, search and analyze your AI coding assistant history, Claude Code, Codex CLI, GitHub Copilot, Gemini CLI, Cursor, OpenCode... What the test found: Frontend JavaScript test suite passes fully (1392 tests, 128 test files). Vite dev server and build are blocked by Node 18.19.1 (needs 20.19+). Rust/Tauri backend cannot compile (no cargo, no webkit2gtk-dev). 23 minutes. | ||||||
| 18 | fable-method | Runs | 100 / 100 | Python | 2,325 | |
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove. What the test found: Repo is a documentation/skill distribution: the install script copies skill files to $HOME/.claude/skills, the repo checks pass (50/50), and all 14 eval trap scenarios work as documented, no dependencies, no build step, no runtime beyond Python 3 and Node.js which are both available. 2 minutes. | ||||||
| 19 | open-cowork | Runs | 100 / 100 | TypeScript | 2,284 | |
Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills, with sandbox isolation, multi-model support, and... What the test found: npm test passes (158 files, 1144 tests) and the Electron app launches on the virtual display, initializes SQLite, loads 5 built-in skills, and serves the NavServer HTTP API returning HTTP 200 with page state. 12 minutes. | ||||||
| 20 | minimax-code | Runs | 100 / 100 | TypeScript | 2,271 | |
An open-source coding agent for your terminal, powered by MiniMax. What the test found: MiniMax Code 0.5.5 installed from source: pnpm install --frozen-lockfile and pnpm build succeed; all verification gates pass including typecheck (0 errors), lint (clean), 4928 capability tests pass, 20 smoke tests pass, CLI --version reports 0.5.5. 9 minutes. | ||||||
| 21 | nimbalyst | Runs | 100 / 100 | TypeScript | 2,096 | |
Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in... What the test found: Nimbalyst monorepo installs, builds (runtime, extension-sdk, collab-bundle), and passes its full vitest unit test suite with 1546 passing test files and 12983 passing tests. 41 minutes. | ||||||
| 22 | BeautifulRust | Runs | 100 / 100 | Python | 2,089 | |
Agent Skills that teach coding agents to write, review, and port idiomatic Rust, plus a tested clippy config. Works with Claude Code, Codex, Copilot, Cursor... What the test found: Rust toolchain 1.100.0 installed; lints/check crate compiles with only expected warning diagnostics; clippy lint config fires all 28 marked lints; skill validation script passes with 0 errors and 0 warnings; 25 unit tests pass; banner generator produces valid procedural art and plugin icon PNGs. 2 minutes. | ||||||
| 23 | agent-purge | Runs | 100 / 100 | JavaScript | 2,051 | |
One persona, many coding agents. Replace or inject system prompts across codex, claude, opencode, grok, omp, hermes, pi, zcode - with a local web console. What the test found: npm install completed, 38 test assertions passed across two test suites, CLI commands (web, doctor, status, ls) all produced correct output with no errors. 1 minute. | ||||||
| 24 | CoreCoder | Runs | 100 / 100 | Python | 1,943 | |
Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder. What the test found: CoreCoder 0.7.0 installed from source via pip, all 185 tests pass, CLI prints help/version, offline demo generates and runs a correct Fibonacci function with passing pytest. 1 minute. | ||||||
| 25 | reason-network | Runs | 100 / 100 | Rust | 1,803 | |
Reason Network: your team's coding agents, talking to each other. The engine behind `reason network`. What the test found: The Rust project builds with cargo build, passes all 29 unit tests and all 98 e2e integration tests across hooks, guided setup, and two-machine iroh networking, and the reason-network binary responds to --version and --help commands. 5 minutes. | ||||||
| 26 | zero | Runs | 100 / 100 | Go | 1,782 | |
The coding agent that answers to you, your model, your machine, your rules. What the test found: Zero 0.9.0 builds from source, all 77 test packages pass (including race-enabled run), the release build tooling works, and the binary responds to --help and version commands. Execution requires a provider API key (zero exec / TUI). 9 minutes. | ||||||
| 27 | zero | Runs | 100 / 100 | Go | 1,782 | |
The coding agent that answers to you, your model, your machine, your rules. What the test found: Zero 0.9.0 builds from source and all tests pass with the race detector on linux/amd64; the binary reports its version, lists all commands, and correctly reports missing provider configuration. 8 minutes. | ||||||
| 28 | spec-kitty | Runs | 100 / 100 | Python | 1,737 | |
Spec-Driven Development with organizational governance. Specs tell AI agents what to build; Charter governs how they build it. Git-native missions, enforceable... What the test found: Spec Kitty CLI 3.2.7rc1 installed in venv at /work/repo/.venv, all major test suites pass with 1903+ tests passing and 0 failures, spec-kitty init creates a working project with Codex agent integration. 82 minutes. | ||||||
| 29 | ouroboros | Runs | 100 / 100 | Python | 1,696 | |
Ouroboros, self-creating AI agent. Born Feb 16, 2026. What the test found: Ouroboros v7.4.4 installs cleanly via uv sync --locked, its uvicorn server answers HTTP 200 on the root endpoint, its CLI enumerates all 12 subcommands, and 511+ default-suite tests pass with zero observed failures across acceptance and system_e2e test files. 73 minutes. | ||||||
| 30 | deja-vu | Runs | 100 / 100 | Go | 1,650 | |
Claude Code, Codex & Cursor memory, local MCP memory, session history search & coding agent handoff. What the test found: The deja binary builds and runs, indexing sessions from synthetic Claude fixtures, answering search queries in both plain-text and JSON formats with correct schema_version 2 output, and listing 35 supported coding-agent harnesses via the sources command. 77 minutes. | ||||||
| 31 | oh-my-agent | Runs | 100 / 100 | TypeScript | 1,472 | |
Agent skills and specialist teams for Claude Code, Codex, Cursor and other coding agents. Load one skill or install domain presets, project hooks and parallel... What the test found: oh-my-agent v13.2.1 builds successfully, the oma CLI binary prints version 13.2.1, and all 4264 tests in 323 test files pass with no failures. 53 minutes. | ||||||
| 32 | openpets | Runs | 100 / 100 | TypeScript | 1,402 | |
Local first, desktop companion platform with animated pets, plugin SDK and coding-agent integrations. What the test found: pnpm check passes for the full workspace: packages/client, agent-events, pet-format, cursor, sdk, zed, claude, opencode, openclaw, mcp, cli, and apps/desktop all typecheck, build, and run their test suites with zero failures. 37 minutes. | ||||||
| 33 | weave | Runs | 100 / 100 | Rust | 1,364 | |
Entity-level git merge driver. Resolves false conflicts git invents when independent agents edit the same file. ~95% reduction vs. line-based merge. What the test found: weave 0.5.4 builds from source, all 505 tests pass, weave and weave-driver binaries run correctly and perform entity-level semantic merges on Python and JavaScript files with clean auto-merges for independent changes and structured conflict markers for real collisions. 13 minutes. | ||||||
| 34 | helmor | Runs | 100 / 100 | TypeScript | 1,305 | |
Open-source local workbench for multi-agent software development. What the test found: Helmor frontend builds (vite success), sidecar tests pass (418/419), frontend tests pass (883/883 across 87 files), Rust library tests pass (1557/1558 with 1 pre-existing env-var-comparison failure). 40 minutes. | ||||||
| 35 | repository-harness | Runs | 100 / 100 | Rust | 1,272 | |
Turn any repo into an agent-ready workspace for Claude Code, Codex, Cursor, and other coding agents. What the test found: The repository builds, all 30 unit and integration tests pass, the full pre-merge validation suite passes, and the harness binary successfully installs, inspects, and diagnoses a fresh core repository end to end. 5 minutes. | ||||||
| 36 | open-steps | Runs | 100 / 100 | Shell | 1,271 | |
Plain-language agent skills for Claude Code, Codex, Cursor and Gemini CLI: honest session reports, straight verdicts, steps you can follow. MIT. What the test found: Open Steps 8 skills installed for Codex CLI, both hooks wired, routing block active, all 287 tests (193 hook + 94 eval) pass with zero failures, and the doctor.sh check reports no faults. 2 minutes. | ||||||
| 37 | building-a-coding-agent-from-scratch-course | Runs | 100 / 100 | Python | 1,237 | |
Learn harness engineering by building Claude Code from scratch. Free, open-source course: 8 articles, 6 videos, 1 codebase. What the test found: Installed and built with uv, 2978 unit tests and 80 integration tests pass, format and lint clean, decode CLI reports version 0.1.0. 5 minutes. | ||||||
| 38 | PiDeck | Runs | 100 / 100 | TypeScript | 1,237 | |
PiDeck 是一个开源的桌面工作台,用于在本地项目目录中统一管理 PI | DSH | ACP Agent 会话,并支持导入 Codex、Claude 本地会话以便统一浏览和恢复。支持多项目工作区、会话历史、Git 集成、内置终端、模型配置和插件管理,基于 Electron 构建。 What the test found: PiDeck v0.7.7 builds from source, TypeScript typechecks, and launches as an Electron desktop app with Electron 43.4.0 on Node 22.19.0. npm install produces 1583 packages, npm run build creates renderer and main process artifacts in out/, and tests pass. Only missing dependency is the external pi CLI binary for full... 10 minutes. | ||||||
| 39 | ctx | Runs | 100 / 100 | Rust | 1,189 | |
Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions. What the test found: ctx 2.0.5 builds from source with Rust 1.97.1, all 240 unit tests pass, and the CLI binary runs all core commands (version, doctor, status, sift, setup, graph, search) on Ubuntu 24.04 overlayfs container. 26 minutes. | ||||||
| 40 | aws-agent-skills | Runs | 100 / 100 | Python | 1,173 | |
AWS Skills for Agents What the test found: Python dependencies installed, all 18 AWS skill SKILL.md files present, and the AWS doc update checker runs successfully against all 18 service RSS feeds plus What's New feed, correctly tracking updates via last-check.json. 1 minute. | ||||||
| 41 | vibecode-pro-max-kit | Runs | 100 / 100 | JavaScript | 1,173 | |
Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders, self-improving context memory, 15 agents... What the test found: Node 22 installed, resolve-manifest.js fixed (exclude bug), e2e assertions widened: all 4 e2e tests pass, install succeeds end-to-end with discover-skills OK, compute-sync-plan reports full sync (0 stale/0 missing). 28 minutes. | ||||||
| 42 | CORAL | Runs | 100 / 100 | Python | 1,144 | |
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution... What the test found: coral 0.7.22.dev7+g0123dfb93.d20261118 installed in editable venv, 740/741 tests pass, CLI commands (init, validate, --version, --help) all work. 20 minutes. | ||||||
| 43 | dsh-browser | Runs | 100 / 100 | TypeScript | 1,119 | |
Chrome sidebar extension that lets DeepSeek Harness operate your browser directly, no vision capabilities required. 一款 Chrome 侧边栏扩展程序,可让 DeepSeek Harness... What the test found: Bridge plugin and Chrome MV3 extension build, typecheck, and both test suites pass (14+50 suites, 140+388 tests). The dsh web CLI cannot boot due to an upstream exitOverride Commander bug in @deepseek-ai/dsh 0.1.5-rc.2. 8 minutes. | ||||||
| 44 | parallel-code | Runs | 100 / 100 | TypeScript | 1,104 | |
Run Claude Code, Codex, Copilot and other agent CLIs in parallel worktrees, then check what each one did before you merge. What the test found: The project installs, compiles, and all 4818 tests pass on Node 22; the Electron app launches on the virtual display and initializes all IPC handlers. 10 minutes. | ||||||
| 45 | EnterpriseAgentFramework | Runs | 100 / 100 | Java | 1,057 | |
ReachAI企业级智能体开发平台:快速、安全完成已有业务系统智能化改造,让 AI 在 OA、ERP、CRM 等原系统中查数据、填表单、办业务。ReachAI: Quickly and securely bring AI to existing enterprise systems, enabling AI to... What the test found: Backend builds cleanly and all 2246 unit/integration tests pass across 9 Maven modules. Frontend builds with npm run build and 453 of 454 vitest tests pass across 10 test suites (1 pre-existing timezone-dependent dashboard test fails in UTC). 34 minutes. | ||||||
| 46 | agenttrail | Runs | 100 / 100 | JavaScript | 1,051 | |
Local observability for AI coding agents. Agenttrail Map shows your project as a live map of what each agent is working on, in the browser or natively in Herdr. What the test found: Agenttrail Kitchen installs, builds, passes all 71 tests, serves the example 3D view on port 4780 (HTTP 200), and launches the Map view on port 5330 (HTTP 200); the checked package works for offline install and file observation. 3 minutes. | ||||||
| 47 | easy-agent | Runs | 100 / 100 | TypeScript | 1,030 | |
Production-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic... What the test found: Easy Agent v0.1.1 installs, typechecks, builds, runs all 68 offline production tests successfully, and the binary launches on Node 22. A valid ANTHROPIC_AUTH_TOKEN is required for LLM-backed usage. 9 minutes. | ||||||
| 48 | herdr-reviewr | Runs | 100 / 100 | Rust | 1,016 | |
Review your agent's diff in a terminal pane and send comments back to Claude Code, Codex, OpenCode or Pi. A herdr plugin. What the test found: The Rust project builds, all 1009 tests pass, the release binary launches as a TUI under a PTY and quits cleanly, and the plugin config resolution works. 13 minutes. | ||||||
| 49 | codeAgent | Runs | 100 / 100 | Python | 1,012 | |
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs... What the test found: All 67 verify checks pass. The project installs, builds, and the verify suite runs to completion without mocks. The app launches (exit 0) under headless mode but requires a TTY + API key for interactive use. 3 minutes. | ||||||
| 50 | SeeCode | Runs | 100 / 100 | JavaScript | 1,000 | |
Animated, explorable diagrams for Claude and other coding agents, from a short JSON spec. What the test found: SeeCode 0.6.1 CLI works fully: render, validate, types, export (SVG), import, scan, config, and doctor commands all return valid JSON responses. Test suite passes 215/226 tests (11 skipped due to no browser). 2 minutes. | ||||||
| 51 | gooey-pi | Runs | 100 / 100 | TypeScript | 981 | |
Desktop workspace for Pi, OMP, and Prime Agent What the test found: GooeyPi builds, all 165 vitest unit test files pass (1927/1928 tests), and all 66 Playwright Electron e2e tests complete with 63 passed, 0 failed, 3 macOS-specific skipped. 72 minutes. | ||||||
| 52 | pi-web | Runs | 100 / 100 | TypeScript | 960 | |
Web UI for Pi Coding Agent that keeps sessions alive in real workspaces. What the test found: The project installs, builds, passes all 420 test files (4463/4465 tests pass), and both the web server and session daemon start and respond correctly. 8 minutes. | ||||||
| 53 | codealmanac | Runs | 100 / 100 | TypeScript | 949 | |
A codebase wiki for AI coding agents. Captures what the code can't say: decisions, flows, invariants, gotchas. What the test found: codealmanac 0.4.7 is installed and functional: all 564 tests pass, ruff linting passes, the CLI reports version 0.4.7, doctor shows green across install/python/database/manual/index/health, and validate confirms the repo's own 71-page wiki is valid. 1 minute. | ||||||
| 54 | agent-plugins | Runs | 100 / 100 | Python | 948 | |
Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS. What the test found: mise installs all tools cleanly; lint, format check, manifest validation, cross-reference validation, and reference integrity check all pass; 125 Python unit tests (safe_query builder and functional eval scripts) pass exercising real plugin source code. 4 minutes. | ||||||
| 55 | memorix | Runs | 100 / 100 | TypeScript | 942 | |
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes... What the test found: Memorix v1.9.6 builds, installs, and runs in this container. The CLI, MCP server (stdio + modern), and bundled memcode agent all start correctly. The full test suite passes (3177/3181 tests). Memory store and search lifecycle verified end-to-end. 8 minutes. | ||||||
| 56 | pi-pocket | Runs | 100 / 100 | TypeScript | 877 | |
A durable, multiplayer, mobile-first web app for Pi agents, built on Pi Durable What the test found: Pi Pocket installed, type-checked, tested (412/0/115), and launched on port 8790 returning HTTP 200. The app's sign-in URL, access controls, and terminal UI all work. 115 browser-UI tests skipped because no Chromium is available in this container; all server tests pass with real Pi Durable storage and a scripted model. 4 minutes. | ||||||
| 57 | okf-agent-memory | Runs | 100 / 100 | Go | 871 | |
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive... What the test found: The okf binary compiles, runs, validates its own knowledge bundle with zero errors/warnings/orphans, performs BM25 semantic search across the knowledge corpus returning correct results, and all 7 Go packages (including vault, sync, okf core, CLI, and AAG linter) pass their full test suites with no failures and no race... 4 minutes. | ||||||
| 58 | hippo-memory | Runs | 100 / 100 | TypeScript | 794 | |
One memory for every agent you'll ever use. Hippo writes what you teach a coding agent into a store in your repo, and your other agents read that same store. What the test found: npm install, npm run build (tsc), and npm test (vitest run) all succeed with 4212 passing tests. The hippo CLI binary runs and reports version 1.52.8. The doctor check reports only that no store has been initialized (expected in a fresh checkout) and that Claude Code is absent, which are not errors. 7 minutes. | ||||||
| 59 | dao-code | Runs | 100 / 100 | TypeScript | 788 | |
Open-source TypeScript terminal coding agent for DeepSeek-V4, builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering... What the test found: Build compiles cleanly, the binary starts and shows the Taoji welcome screen and language selection wizard, and 1830 real unit tests pass covering tools, memory, skills, MCP, sessions, config, commands, hooks, approvals, permissions, i18n, scheduling, and TUI components. 12 minutes. | ||||||
| 60 | codanna | Runs | 100 / 100 | Rust | 764 | |
Local code intelligence MCP server and CLI for AI coding agents What the test found: codanna builds from source in this container, passes all 1823 tests across 10 test suites, the CLI binary runs and reports its version, init/index/symbol-search/semantic-search/serve commands all function, and the HTTP server answers health checks with 200 OK, all with no external API dependencies. 22 minutes. | ||||||
| 61 | agentacct | Runs | 100 / 100 | Python | 758 | |
See what your coding agents did and what it cost. Breaks each task down into work steps, tools used, files changed, tests run, time and tokens spent... What the test found: agentacct 0.12.5 installs via venv, CLI (agentacct --version prints 0.12.5), onboard runs successfully writing MCP config and hooks, the local API starts on 127.0.0.1:8765 and returns 200 on /health with real session usage data ingested, and the test suite passes 4887 of 4895 tests. 76 minutes. | ||||||
| 62 | mcode-stack | Runs | 100 / 100 | JavaScript | 739 | |
The workflows and skills the MiniMax Code team uses to build MiniMax Code. Open source, install and use. What the test found: Both ronny and jiachen stacks install correctly as Codex plugins with all skills present, and pass both the repository's structural checks and the official MiniMax Code Plugin V1 validation. 3 minutes. | ||||||
| 63 | MegaMemory | Runs | 100 / 100 | TypeScript | 737 | |
Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer. What the test found: MegaMemory v1.6.2 builds, all 153 tests pass, the MCP stdio server responds to all 9 tool calls, and the web graph explorer serves HTTP 200. 2 minutes. | ||||||
| 64 | brain.md | Runs | 100 / 100 | JavaScript | 721 | |
A persistent, file-based memory layer for coding agents, give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via a... What the test found: All 50 project tests pass. Every CLI subcommand runs correctly: init scaffolds BRAIN.md and brain directory, CRUD page operations work end-to-end, hooks install/uninstall cleanly, and wiring creates agent config files. Zero external dependencies or credentials required. 4 minutes. | ||||||
| 65 | agent-hud-open | Runs | 100 / 100 | Rust | 717 | |
A HUD for Claude Code, Codex and 25 more coding agents. Know your quotas, tokens and sessions at a glance, answer requests and jump back in one click. On Mac... What the test found: Rust engine binary builds in debug and release modes, responds correctly to JSON-lines snapshot and system RPCs, and 731 Rust test groups pass with zero failures; installer tests pass 7/7; all TypeScript packages typecheck; desktop Tauri build is blocked on Linux by missing system-dev packages (glib, webkit2gtk, soup)... 9 minutes. | ||||||
| 66 | sqz | Runs | 100 / 100 | Rust | 679 | |
Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro... What the test found: The sqz workspace builds and its 1715 tests pass; sqz 2.1.1 runs, compresses with byte-exact expand, the sqz-mcp stdio server completes the MCP initialize handshake and lists 7 tools, and the local proxy answered HTTP 200 on POST /v1/chat/completions with a compressed body. 13 minutes. | ||||||
| 67 | wcgw | Runs | 100 / 100 | Python | 679 | |
Shell and coding agent on mcp clients What the test found: wcgw 5.6.5 is fully installed, all 63 pytest tests pass, the MCP server entry point (wcgw) and CLI (wcgw_local) both respond to --help, and all package imports resolve cleanly. 2 minutes. | ||||||
| 68 | casbin-gateway | Runs | 100 / 100 | Go | 650 | |
See what every AI coding agent on your machine is doing, and whether the API behind it is the one you paid for. Claude Code, Codex, Cursor, Gemini CLI and... What the test found: Server binary installed via curl|bash and starts on localhost:17000; sign-in (admin/123), API endpoints, relay token, provider CRUD, and LLM relay (non-stream and streaming) all verified end-to-end with a mock OpenAI upstream returning HTTP 200 with correct response body. 10 minutes. | ||||||
| 69 | graphicle | Runs | 100 / 100 | Rust | 620 | |
Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client. What the test found: Graphicle 0.1.5 installed via prebuilt binary, setup completed successfully on the repository (code graph built, agent connected, hooks installed, web app serving HTTP 200), all core commands function without errors. 4 minutes. | ||||||
| 70 | theia-ide | Runs | 100 / 100 | TypeScript | 620 | |
The Theia IDE: an open-source, AI-native IDE for desktop and browser, built on the Theia Platform and Theia AI. Bring your own key for any LLM, with MCP, Agent... What the test found: Theia IDE browser app builds with 0 errors and starts serving HTTP 200 with Theia IDE HTML on the configured port. 15 minutes. | ||||||
| 71 | claw-orchestrator | Runs | 100 / 100 | TypeScript | 618 | |
Run Claude Code, Codex, Antigravity, Grok Build and OpenCode behind one runtime, and a run only counts as done when checks it didn't write pass. Cross-engine... What the test found: Project builds with npm run build, all 1724 vitest tests pass, CLI binary runs and reports version 7.5.5 with all 15 commands listed. 4 minutes. | ||||||
| 72 | abacusai-bot | Runs | 100 / 100 | TypeScript | 610 | |
100% free, open-source personal agents for your messaging apps, tools, and services What the test found: The AbacusAI Bot desktop app builds from source, 3920 unit tests pass across all packages, and the Electron app launches to the authentication screen on the virtual display. 4 minutes. | ||||||
| 73 | mcp-pointer | Runs | 100 / 100 | TypeScript | 599 | |
MCP tool: let you point at DOM elements for your favorite agentic coding tool. Let AI see what you see. What the test found: Full monorepo builds clean. Server package (23/23 tests passing) and Chrome extension package both build. CLI binary starts, prints leader banner, and accepts WebSocket connections. 2 minutes. | ||||||
| 74 | better-design | Runs | 100 / 100 | TypeScript | 592 | |
Open-source design MCP server and shadcn/ui registry: every Better Design design system, with design tokens, UI principles and accessibility rules for Claude... What the test found: The registry repo builds and passes its suite (22 tests, typecheck clean, generator idempotent), and the published better-design CLI is installed with a live free API key that the hosted MCP server accepted, with the MCP server wired into ~/.codex/config.toml. 3 minutes. | ||||||
| 75 | termaid | Runs | 100 / 100 | Python | 589 | |
Render Mermaid diagrams in your coding agent What the test found: termaid v0.12.0 installed in a Python 3.12.3 venv via pip install -e '.[dev]'; the full test suite (4206 tests) passes; the CLI renders flowcharts from stdin, and the Python render() API produces correct output. 1 minute. | ||||||
| 76 | agentbox | Runs | 100 / 100 | TypeScript | 586 | |
Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud What the test found: The AgentBox monorepo builds and all 46 package test suites pass (0 failures, 0 cached failures), the agentbox CLI binary responds with correct version/help output, and rsync is available at /home/runner/.npm-global/bin/rsync for the sync-layer tests. 19 minutes. | ||||||
| 77 | smart-ralph | Runs | 100 / 100 | Shell | 565 | |
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow. What the test found: Smart Ralph plugin suite fully passing: 342 Bats tests and 13 Python tests all green, with stop-watcher, state management, integration, prototype phases, interview framework, phase gates, workflow guardrails, and platform validation all verified. 23 minutes. | ||||||
| 78 | OpenVLHarness | Runs | 100 / 100 | Python | 563 | |
Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory What the test found: Package openvlharness 0.1.0 installed in a Python 3.12 venv with all extras; all 503 tests pass (0 failures, 0 skips); the tool router FastAPI app creates and serves /health (200 OK) and /tools endpoints; the openvlharness-eval CLI entrypoint prints help text correctly. 5 minutes. | ||||||
| 79 | appworld | Runs | 100 / 100 | Python | 557 | |
🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper. What the test found: AppWorld installs and builds; all 1851 package tests pass; the CLI (appworld --version prints 0.2.0.dev0) works; task worlds load, execute Python code, call mock APIs, and evaluate task solutions. 37 minutes. | ||||||
| 80 | zhikuncode | Runs | 100 / 100 | Java | 549 | |
Codex/Claude Code/Cursor的开源增强版,专注一句话实现复杂长程任务(教育、编程、办公、生活、娱乐、游戏)。部署在你自己的服务器上,团队用浏览器打开就能编程, 包括手机。CLI & Web UI 双入口,Multi-Agent 协作,原生直连千问/DeepSeek... What the test found: Python FastAPI service runs on port 8000 with health endpoint OK; Java Spring Boot backend runs on port 8080 with actuator health status UP and SQLite global+project databases operational; React frontend builds cleanly with 207/223 tests passing; all three tiers (Python 105/107, Java 2392/2454, React 207/223) pass... 18 minutes. | ||||||
| 81 | ai-video-marker | Runs | 100 / 100 | Python | 548 | |
🎬 AI 视频制作与 AIGC 创作工作流(AI Video Creation Workflow)|用 AI 制作视频、像素动画与漫画短片|分镜、素材、配乐、模板与可运行 Python 示例|Blender 分层动画与剪映制作方法 What the test found: Full test suite passes, all validation tools pass, and the harbor robot video pipeline produces valid H.264 MP4 video with correct frame count, no decode errors, and bundled audio. 5 minutes. | ||||||
| 82 | runner | Runs | 100 / 100 | Rust | 548 | |
Where terminal agents work together. Claude Code, Codex, Copilot CLI and pi on the same task, in one mission, each keeping its own TUI in a real terminal. What the test found: The Rust workspace builds successfully for all Linux-compatible crates (runner-core, runner-backend, runner-cli, runner-terminal). All 1318+ tests pass. The runner CLI binary outputs version 0.12.9 and responds to all subcommands. 16 minutes. | ||||||
| 83 | Semantic-Anchors | Runs | 100 / 100 | JavaScript | 547 | |
A curated catalog of 230+ semantic anchors: well-defined terms like arc42, TDD London School or tracer bullet that activate deep, consistent knowledge in LLMs... What the test found: Website tests pass (22/22 files, 332/332 tests), production build completes (metadata extraction, docs rendering, vite build, prerendering, JSON-LD injection), and vite preview serves the site at HTTP 200 on /Semantic-Anchors/. 10 minutes. | ||||||
| 84 | happyhands | Runs | 100 / 100 | JavaScript | 534 | |
Open-source, AI-assisted UI design review for coding agents. Inspect screenshots, scope code changes and compare results in a local workbench. Alpha. What the test found: HappyHands workbench installs, builds, serves on port 4190, passes all 641 tests and 28 regression cases with Node 22.15.0 via portable binary. 5 minutes. | ||||||
| 85 | gwq | Runs | 100 / 100 | Go | 484 | |
🌳 Git worktree manager with fuzzy finder - Work on multiple branches simultaneously, perfect for parallel AI coding workflows 🍋 What the test found: The gwq binary builds and installs with a downloaded Go toolchain, runs its full test suite (go test ./... exits 0 with all ok), and its add/list/get/status/exec/remove commands operate on real git worktrees as confirmed by git worktree list and command output. 4 minutes. | ||||||
| 86 | Async | Runs | 100 / 100 | TypeScript | 476 | |
IDE, A native-feeling AI coding workspace that blends chat, planning, agent execution, and project navigation into a unified desktop experience. What the test found: npm install completes, full build (typecheck + esbuild + vite) succeeds, all 117 test files (709 tests) pass, and the Electron app starts with the dist bundle rendering the agent window via did-finish-load. 8 minutes. | ||||||
| 87 | Gito | Runs | 100 / 100 | Python | 476 | |
An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues, such as security vulnerabilities, bugs, and maintainability... What the test found: All 157 tests pass and gito CLI version command runs from a Python 3.12 venv, with only the version-shell test requiring a PATH fix. 3 minutes. | ||||||
| 88 | agent-spec | Runs | 100 / 100 | Rust | 464 | |
`agent-spec` is an AI-native BDD/spec verification tool for task execution. What the test found: agent-spec 1.4.0 builds and all 1111 tests pass on Rust 1.98.1 with no modifications. 3 minutes. | ||||||
| 89 | intent | Runs | 100 / 100 | JavaScript | 463 | |
Open-source workspace for coding agents: specialists plan, then Claude Code, Codex & Cursor build in parallel, on your machines or in the cloud. What the test found: intentd 0.11.190 builds and runs on Linux x86_64 with Rust 1.96.0; the backend daemon binary (390 MB debug) compiles, prints version, and passes 140+ tests across 14 crate test suites with zero failures. 71 minutes. | ||||||
| 90 | Frame | Runs | 100 / 100 | JavaScript | 461 | |
ADE( Agentic Development Environment) The spec-driven environment for AI coding agents, where your planning becomes lasting, shared project context. What the test found: All 1171 tests pass. The Electron app launches on the virtual display (Xvfb :99), creates its window menu, and runs without crashing until terminated. 12 minutes. | ||||||
| 91 | wmux | Runs | 100 / 100 | TypeScript | 459 | |
The ADE for AI agents. Automate everything else. Do your true work. | ||||||
| 92 | dryforge | Runs | 100 / 100 | Python | 452 | |
Bounded-autonomy plugin harness for agents. Intent to implementation: ready, then go. What the test found: Repository builds all 5 platform targets (Claude, Codex, Grok, Agent Plugins, Antigravity), passes full verification suite, and the Codex plugin installs and enables correctly in the Codex CLI. 3 minutes. | ||||||
| 93 | harness-remote | Runs | 100 / 100 | JavaScript | 449 | |
Native-session control plane for Codex, Claude Code, OpenCode, PI and many others. Run, resume and hand off coding sessions across your machines. What the test found: Bridge server launches, listens on configured port, authenticates via Basic Auth, and responds to API routes; all 600 bridge tests pass with zero failures. 4 minutes. | ||||||
| 94 | apm-studio | Runs | 100 / 100 | TypeScript | 438 | |
Local editor for importing, managing, running, and injecting APM-backed assistant packages. What the test found: APM Studio installs, passes all 915 tests, builds client and server, and serves HTTP 200 on its API and frontend endpoints. 2 minutes. | ||||||
| 95 | pi-desktop | Runs | 100 / 100 | TypeScript | 426 | |
Pi Desktop: a free, open source desktop GUI for the Pi coding agent and oh-my-pi. Chat, edit files, run a terminal, and review diffs in one window. Linux... What the test found: Pi Desktop v0.1.9-alpha builds from source, passes all 1246 tests, and renders its GUI correctly on a virtual display. 5 minutes. | ||||||
| 96 | turbo | Runs | 100 / 100 | Shell | 426 | |
Ship changes of any size with confidence. An agentic software factory for Claude Code and Codex. What the test found: Turbo plugin installed and enabled from local marketplace at /work/repo, SessionStart hook loads Turbo Rules into sessions, all 69 skills present with valid SKILL.md files, .turbo/ added to global gitignore, user config created at ~/.turbo/config.json. 4 minutes. | ||||||
| 97 | opencode-primer | Runs | 100 / 100 | JavaScript | 418 | |
Master OpenCode, the open-source AI coding agent, setup, agents, skills, plugins, MCP, Zen & headless CI. What the test found: All 17 markdown files pass markdownlint, codespell, and link checks; opencode.json and tui.json are valid JSON; the repo is clean with no working tree changes. 3 minutes. | ||||||
| 98 | openlive | Runs | 100 / 100 | TypeScript | 414 | |
Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) runs locally. An... What the test found: The OpenLive monorepo installs, builds, type-checks, runs all 82 tests successfully, and serves the web UI on port 3000 with the agent service on port 8787, both returning HTTP 200. 4 minutes. | ||||||
| 99 | pi-app | Runs | 100 / 100 | TypeScript | 409 | |
Desktop app for the pi coding agent: streaming timeline, Git review with hunk staging, session tree, native UI for pi extensions. Windows · macOS · Linux. pi... What the test found: pi Desktop 0.6.0 builds from source, all 1384 unit tests pass, all 275 contract tests pass, typecheck passes, and the Electron app launches on the virtual display. 5 minutes. | ||||||
| 100 | the-pair | Runs | 100 / 100 | Rust | 391 | |
Open-source AI pair programming desktop app: a read-only Mentor and an Executor agent cross-check each other's code to catch AI mistakes before they land... What the test found: All npm test suites pass (537 JS + 187 UI + 849 Rust = 1573 tests). TypeScript typechecks pass. Vite build succeeds. 9/10 headless e2e-web tests pass (1 flaky keyboard focus test). The Tauri desktop binary does not launch in this headless container due to missing webkit2gtk runtime libraries not installable without... 51 minutes. | ||||||
| 101 | developer-kit | Runs | 100 / 100 | Python | 372 | |
Modular plugin marketplace for Claude Code and agentic CLIs, with validated, spec-driven skills, agents, commands, and workflows for Java, TypeScript, Python... What the test found: All 211 tests pass, the validator CLI validates all 744 files without errors, and the Codex CLI install target copies 151 skills and generates an AGENTS.md index file. 4 minutes. | ||||||
| 102 | dscode | Runs | 100 / 100 | TypeScript | 369 | |
Coding agent powered by DeepSeek. What the test found: DSCode 0.3.6 installs from source, builds via pnpm build (TypeScript compilation succeeds), all 206 tests pass (4 platform-specific tests skipped on Linux), and the CLI launches reporting version 0.3.6 with a full usage page. 7 minutes. | ||||||
| 103 | localix-cli | Runs | 100 / 100 | Rust | 369 | |
Localix CLI: an ultrafast agent runtime for coding and CI, in Rust. One binary under 4 MB, any model. The command is llx. What the test found: The Rust project builds from source with cargo, the llx binary launches and reports version 0.6.2, all 1365 unit/integration tests pass, the release binary is 3.58 MiB (under the 4 MB target), and the app runs end-to-end with the pre-configured OpenRouter API key: llx exec returns answers, llx doctor confirms... 13 minutes. | ||||||
| 104 | kelos | Runs | 100 / 100 | Go | 360 | |
Kelos - The Kubernetes-native framework for orchestrating autonomous AI coding agents. What the test found: All unit tests (45 packages) and integration tests (173 specs) pass, the CLI binary builds and answers commands, and the controller, webhook, and install CRDs work correctly against a real Kubernetes API server. 11 minutes. | ||||||
| 105 | crew44 | Runs | 100 / 100 | Go | 358 | |
Orchestrate a crew of specialist AI agents in one local-first workspace. Each role on its best model, with memory and skills that compound. Free, MIT. What the test found: Daemon builds and serves health endpoint at 127.0.0.1:8080; all 16 Go test packages and all 341 frontend vitest tests pass with Node 22.23.4 and Go 1.26.1. 8 minutes. | ||||||
| 106 | pi-desktop | Runs | 100 / 100 | TypeScript | 355 | |
A local-first, cross-platform Electron desktop workspace for Pi Coding Agent, with sessions, project files, browser tools, skills, plugins, and messaging... What the test found: Pi Agent Desktop v0.3.0 builds, all 1106 tests pass, and Electron smoke test verifies agent-host (pi=0.87.1) with all 12 function domains (renderer, RPC, session, worktree, git, watch, download, skills, channels, chat-appearance, toolchain) passing. 11 minutes. | ||||||
| 107 | genie | Runs | 100 / 100 | TypeScript | 354 | |
Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it. What the test found: Genie CLI builds and runs (version 6.261109.6), 3639 of 3667 tests pass, typecheck and all lint checks pass, 24 pre-existing failures are all environment constraints (Node 18 for .ts plugin builds, missing real genie binary for installer promotion tests, 3 intermittent timeouts). 64 minutes. | ||||||
| 108 | Orkas-VideoStudio | Runs | 100 / 100 | TypeScript | 350 | |
Open-source alternative to Claude Motion and CapCut: your coding agent (Claude Code, Codex, Cursor) edits footage, designs motion graphics, adds narration and... What the test found: The repository installs, builds, typechecks, benchmarks, and passes all 282 unit tests plus 47 E2E tests including a real three-scene video production pipeline that composes HTML motion graphics, renders via HyperFrames 0.7.60 with chrome-headless-shell, burns captions with ffmpeg, and passes the delivery... 12 minutes. | ||||||
| 109 | stash | Runs | 100 / 100 | Python | 345 | |
Open-source infrastructure for agents that learn from experience. Capture production traces and turn lessons into reusable knowledge and skills. What the test found: All four test suites pass (CLI 259, frontend 336, www 14, backend 184), both Next.js apps build, and ruff lint/format passes. 24 minutes. | ||||||
| 110 | armory | Runs | 100 / 100 | Python | 343 | |
Curated, production-grade skills for AI coding agents. Battle-tested workflows for developers who use AI seriously. What the test found: uv sync installs all dependencies, 369 repo-level and 348 package-level tests pass, all 145 packages install to ~/.claude/, eval validation and search scripts operate correctly, templates are in sync. 3 minutes. | ||||||
| 111 | lazyskills | Runs | 100 / 100 | Go | 340 | |
mission control for agent skills What the test found: LazySkills binary builds from source, passes its full test suite (including race detector), passes all CI checks (gofmt, vet, deadcode), and its non-TUI commands (doctor, find, update, version) execute correctly against both the filesystem and the external skills.sh registry API. 3 minutes. | ||||||
| 112 | funzzy | Runs | 100 / 100 | Rust | 331 | |
Gives developers and coding agents one reliable edit loop What the test found: All 931 unit tests pass, both funzzy and fzz debug/release binaries build and run correctly, config validation and schema output work as documented. 9 minutes. | ||||||
| 113 | packmind | Runs | 100 / 100 | TypeScript | 327 | |
Packmind seamlessly captures your engineering playbook and turns it into AI context, guardrails, and governance. What the test found: pnpm install completed, tsconfig.base.effective.json generated, all 22 backend-test projects pass (694 suites, 15067 tests), frontend passes (165 suites, 2532 tests), packmind-cli builds and runs (version 0.36.1-next), eslint lint passes on all checked projects. 10 minutes. | ||||||
| 114 | agentfs-claude | Runs | 100 / 100 | TypeScript | 324 | |
Run Claude Code/Codex within AgentFS, orchestrated by LlamaIndex Workflows What the test found: TypeScript builds cleanly, all 10 tests pass, and the MCP server starts and serves all 5 filesystem tools (read_file, write_file, edit_file, file_exists, list_files) over HTTP on port 3000. 6 minutes. | ||||||
| 115 | golembot | Runs | 100 / 100 | TypeScript | 324 | |
Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Discord, Feishu, DingTalk, WeCom, WeChat, with any LLM... What the test found: pnpm install succeeds, tsc build succeeds, all 1336 unit tests pass, the CLI binary prints help and version, the HTTP serve mode listens on a port and answers /health with 200, and the gateway mode starts with all channel stubs and answers /health with 200. 2 minutes. | ||||||
| 116 | ai-prd-workflow | Runs | 100 / 100 | Python | 317 | |
RFC-driven development for AI coding agents: idea or existing codebase → verified PRD → features → rules → sequenced RFCs → reviewed code. Agent Skills for... What the test found: Repository builds all 11 Agent Skills from prompt sources, installs into .claude/skills and .agents/skills without errors, passes all 18 checks across three test suites, and versions are consistent at 3.0.0 across install.sh, plugin.json, and CHANGELOG.md. 2 minutes. | ||||||
| 117 | compose-skill | Runs | 100 / 100 | Shell | 307 | |
Compose Skill (Compose Kit): agent skills for Jetpack Compose & Compose Multiplatform. Makes Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode write... What the test found: All 90 guard tests pass: 11 shell-guard scripts validate MVI/Koin/Nav3 architecture conventions on good fixtures and correctly reject bad fixtures, frontmatter schema validation passes on all 7 skills, the new-feature scaffold builds correctly and passes all checks after SEAM markers are implemented, install-guards.sh... 1 minute. | ||||||
| 118 | cupcake | Runs | 100 / 100 | Rust | 305 | |
A native policy enforcement layer for AI coding agents. Built on OPA/Rego. What the test found: Cupcake 0.5.2 builds from source, the CLI binary runs (cupcake --version prints 0.5.2), supports 4 harnesses (Claude Code, Cursor, Factory AI, OpenCode), compiles Rego policies into WASM via OPA, evaluates hook events against builtin policies (git_pre_check, protected_paths, git_block_no_verify), and returns... 19 minutes. | ||||||
| 119 | nopus | Runs | 100 / 100 | TypeScript | 305 | |
Deterministic prose checks for clearer coding-agent responses What the test found: nopus installs, builds, and passes all 55 tests on Node 26 with all 5 normalized datasets verified and valid plugin artifacts produced. 3 minutes. | ||||||
| 120 | herdr-auto-title | Runs | 100 / 100 | Go | 299 | |
Automatically name Herdr tabs and panes from your current work: Git branch, running process, and Claude Code, Codex, Pi, Grok, Hermes and Antigravity sessions... What the test found: Go 1.24 downloaded from go.dev, project builds with 'go build', all 554 tests pass across 8 packages, binary exits correctly with expected error when run outside Herdr. 6 minutes. | ||||||
| 121 | codev | Runs | 100 / 100 | TypeScript | 298 | |
Codev helps humans and agents co-develop both the context and the code of the project. What the test found: The Codev monorepo builds, all 6210 unit tests pass, and the CLI runs and reports version 3.3.4 with doctor verification succeeding. 13 minutes. | ||||||
| 122 | pi-rust | Runs | 100 / 100 | Rust | 296 | |
Rust-native, library-first coding-agent runtime and terminal CLI inspired by Pi, with composable LLM providers, tools, sessions, and plugin ABI What the test found: Full Rust workspace compiles and all 3176 tests pass; the minimal example runs offline using the faux provider and produces the expected agent transcript; the CLI binary reports version 0.16.0. 13 minutes. | ||||||
| 123 | broccoli | Runs | 100 / 100 | Python | 284 | |
Broccoli turns Linear tickets into shipped PRs, powered by Claude and Codex, running on your own Google Cloud or Blaxel containers. What the test found: Python 3.12 project installs via uv sync --dev, ruff check passes, pytest passes 156/171 offline (15 skipped need PG), FastAPI app serves healthz 200 and processes webhooks against a live Postgres 16 with all migrations applied. 42 minutes. | ||||||
| 124 | acryl | Runs | 100 / 100 | TypeScript | 279 | |
ACRYL (Agent Context Relay Yielding Lifecycles) is a platform for agentic apps: build them with any coding agent inside, run them as desktop, web, cli-tui or... What the test found: Node.js 22.19.0 works with Corepack 0.34.0 (pnpm 11.11.0); 1263 packages installed; 24 workspace packages build, typecheck, and test; the ACRYL CLI help command prints the full interface; the acryl-web --help command works; all headless test suites pass (acryl-control, blends-core, app-persistence... 14 minutes. | ||||||
| 125 | brain0 | Runs | 100 / 100 | Rust | 278 | |
The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read... What the test found: The brain0 monorepo (14 Rust crates, 5 TS packages) builds and all tests pass; the HTTP server serves the GUI and graph/debug APIs correctly. 4 minutes. | ||||||
| 126 | habit-hooks | Runs | 100 / 100 | Python | 276 | |
Automated quality checks that nudge AI coding agents toward better habits What the test found: habit-hooks project installs via uv sync, pnpm install, all 939 tests pass, ruff lints clean, habit-hooks --all runs successfully on the repo itself. 18 minutes. | ||||||
| 127 | skill-validator | Runs | 100 / 100 | Go | 271 | |
Validate Skill content against Agent Skill specification, with additional content density and quality checks. What the test found: All 13 Go packages build and test successfully; the CLI binary runs at version v1.6.2; structure validation, link validation, content analysis, contamination analysis, and the 'check' command all function correctly against the example skill. 2 minutes. | ||||||
| 128 | martin-loop | Runs | 100 / 100 | TypeScript | 263 | |
Run coding agents without babysitting them. Keep jobs focused, bounded, checked and accountable from start to finish. Finally run your agents swarms overnight... What the test found: MartinLoop 0.6.9 builds from source, the martin CLI launches with all subcommands, the SDK imports with all exports, 6 vitest packages pass all tests, and 166/166 script-level release tests pass on Node 20.20.2 with pnpm 10.33.0. 17 minutes. | ||||||
| 129 | probity | Runs | 100 / 100 | TypeScript | 253 | |
TDD enforcement and guardrails for Claude Code, Codex, and GitHub Copilot CLI What the test found: @nizos/probity v1.10.1 builds, its CLI binary (dist/bin.js) prints version and help, and all 60 test files pass (550 tests passed, 26 skipped). 2 minutes. | ||||||
| 130 | openusage | Runs | 100 / 100 | Go | 248 | |
The one dashboard you’ve been looking for, track spend and usage across Claude, Cursor, OpenRouter, Copilot, Gemini, Codex, and more. What the test found: 52/52 Go test packages pass (race detector on), headless subcommands daily/monthly/session/blocks/detect/version all produce correct output with real Codex CLI data, binary builds at 19MB. 6 minutes. | ||||||
| 131 | Vibe_coding_guide | Runs | 100 / 100 | JavaScript | 248 | |
中文优先的 Vibe Coding / AI coding engineering workflow guide: specs, agents, worktrees, skills, CI, and review. What the test found: The static tutorial site installs with zero dependencies, serves HTTP 200 on python3 -m http.server 4173, and works in real headless Chrome: schedule/day navigation, checklist progress persisted in localStorage, and reader mode rendering the markdown course; its only 404 is the optional favicon.ico. 6 minutes. | ||||||
| 132 | meta-llm-charter | Runs | 100 / 100 | TypeScript | 247 | |
Compact operational charter that turns LLM coding agents into disciplined principal engineers. Eleven rules + one meta-rule. What the test found: The eval harness installs and builds cleanly, all 70 harness unit tests pass, all 15 fixture suites match their pinned counts, and a documented bug fix plus the --quiet task implemented over the fixture verified green test runs and correct CLI output in this container. 4 minutes. | ||||||
| 133 | Albatross | Runs | 100 / 100 | Rust | 244 | |
Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud, your keys, one TUI... What the test found: Albatross 2.5.0 builds from source, passes all 712 unit tests, passes cargo fmt and clippy -D warnings, and can run a one-shot prompt against an Ollama-compatible API returning SSE streaming chunks. 18 minutes. | ||||||
| 134 | agentic-os | Runs | 100 / 100 | Python | 242 | |
Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without... What the test found: Full test suite (810 tests) passes, validate.sh reports all PASS, and credential-scan demo runs correctly. 9 minutes. | ||||||
| 135 | unsnooze | Runs | 100 / 100 | JavaScript | 235 | |
Automatically resume Claude Code, Codex CLI, Grok, Qwen Code, Kimi CLI, OpenCode, and Antigravity sessions when 5-hour or weekly usage limits reset, across... What the test found: All 1489 tests pass on Node 20.12.0; the unsnooze CLI responds to --help with full usage output. 14 minutes. | ||||||
| 136 | gograph | Runs | 100 / 100 | Go | 232 | |
Local-only Go static analysis engine with a built-in MCP server. Gives AI coding agents deterministic structural awareness: call graphs, impact analysis... What the test found: Gograph is fully built, all 26 test packages pass, the binary reports version 1.7.5-9e4c8b4 on go1.27.0, and it successfully builds both AST and precise structural graphs of its own repository. 6 minutes. | ||||||
| 137 | CodeKanban | Runs | 100 / 100 | Go | 227 | |
Manage all your terminals and ai coding agents from one unified page. What the test found: Go build succeeds, all 14 test packages pass, server binary CodeKanban runs and responds with 200 on /api/v1/health, and the npm package [email protected] is installed globally. 7 minutes. | ||||||
| 138 | agent-sandbox | Runs | 100 / 100 | Python | 215 | |
Secure local dev environment for collaboration with AI coding agents What the test found: The agentbox CLI binary is built and functional at dist/agentbox-linux-amd64, all 5 Go test packages pass, and all 195 proxy Python tests pass. 4 minutes. | ||||||
| 139 | codex-command-center | Runs | 100 / 100 | TypeScript | 192 | |
A local desktop control center for organizing Codex projects, engineering tasks, sessions, Git changes, Skills, and MCP configuration. What the test found: Frontend build and preview server work. Tauri native build and Rust tests cannot compile because system packages (libglib2.0-dev, libgtk-3-dev, libwebkit2gtk-4.0-dev) are not installed and cannot be installed without root. 3 minutes. | ||||||
| 140 | threadport | Runs | 100 / 100 | TypeScript | 123 | |
Portable, verifiable work state for coding agents What the test found: ThreadPort 0.2.1 built from source, all 523 unit tests pass, the CLI validates schemas, renders capsules, reports diagnostics, and lists targets without errors. 4 minutes. | ||||||
| 141 | agents | Runs | 98.7 / 100 | Python | 42,790 | |
Plugins, agents, skills, and commands for Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi, written once in Markdown and... What the test found: uv sync installs all deps for both projects; pytest suite passes 619/621; all 6 harness generators emit artifacts; codex doctor reports 20/20 checks ok; structural validation passes across 6 harnesses with strict mode. 11 minutes. | ||||||
| 142 | deepseek-harness-desktop | Runs | 98.3 / 100 | JavaScript | 952 | |
Open-source Windows desktop client and GUI for DeepSeek Harness, zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins. What the test found: Dependencies installed, all 40 workspace projects build and typecheck. Script tests 200/200 pass. Desktop test suite 1229/1229 pass (0 fail, 26 skipped). DSH web runtime starts and serves HTTP (401 with auth active). One pre-existing issue: dsh-ssh engine.test.ts needs ssh-keygen (openssh-client) unavailable in this... 22 minutes. | ||||||
| 143 | codex-slides | Runs | 97.5 / 100 | TypeScript | 992 | |
🎨 Open-source AI slide studio inside Codex: image-native decks, every slide a full visual canvas. ⚡ 10+ high-quality slides in ~4, 5 minutes, Fast mode... What the test found: Next.js web app builds with next build, all 67 unit tests pass, dev server serves homepage and 36 API routes on http://127.0.0.1:4311 returning HTTP 200, TypeScript typecheck passes, i18n check passes, MCP probe passes with 38 tools. 10 minutes. | ||||||
| 144 | DeepSeek-Reasonix | Runs | 97.3 / 100 | Go | 36,082 | |
A reliable coding agent for complex software engineering tasks. What the test found: Reasonix builds as a single Go binary (bin/reasonix), answers --help with full usage including CLI/TUI, web, serve, ACP, and bot subcommands, passes all 147+ test packages with 0 failures, and produces valid JSON diagnostics via doctor --json. 19 minutes. | ||||||
| 145 | omnigent | Runs | 97.3 / 100 | Python | 11,489 | |
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents, swap harnesses without... What the test found: The omnigent CLI reports version 0.13.0.dev0, the server listens on TCP and returns HTTP 200 on root/health/OpenAPI endpoints, and 929+ unit tests across 10 module directories pass without failure. 28 minutes. | ||||||
| 146 | cli-continues | Runs | 96.7 / 100 | TypeScript | 1,612 | |
resume any AI coding session in another tool, Claude Code, Copilot, Gemini, Codex, Cursor What the test found: Node.js upgraded to v22.14.0 (via /tmp/), pnpm installed and builds approved, project compiles with tsc with zero errors, all 28 test files pass (917/919), CLI binary functions (help, version, scan, list all work), and biome passes with warnings only. 7 minutes. | ||||||
| 147 | crit | Runs | 96.7 / 100 | Go | 1,351 | |
Review AI coding agents' plans, diffs and running apps in the browser. Local-first, works with any agent. What the test found: Built crit binary compiles, launches an HTTP server on 127.0.0.1, serves /api/health returning 200, auto-detects git changes in feature branches, serves embedded frontend, and the full test suite passes all unit and JS tests except one pre-existing intermittent flake in session lazy-threshold ordering. 42 minutes. | ||||||
| 148 | harnessrouter | Runs | 96 / 100 | Python | 4,406 | |
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and... What the test found: Gateway and runner servers start and respond to health checks; all three test suites (gateway: 622/17, runner: 490/2, protocol conformance: 85/2) pass. 6 minutes. | ||||||
| 149 | qwen-audio-agent | Runs | 96 / 100 | JavaScript | 3,265 | |
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents What the test found: The qwen-audio-agent v1.11.0 project installs, builds, launches a Gateway serving HTTP 200 on port 3101, and passes all 1789 automated tests with zero failures. 9 minutes. | ||||||
| 150 | jevgrep | Runs | 96 / 100 | TypeScript | 3,260 | |
Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context. What the test found: Project installs, builds, lints, type-checks, and all test suites pass cleanly. The jg CLI help screen and version command work. Provider-dependent tests skip gracefully without credentials. 4 minutes. | ||||||
| 151 | Formal-Verification-RSI | Runs | 96 / 100 | Python | 2,913 | |
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for... What the test found: Both verification rungs (Lean 4.23.0-rc2 and Dafny 4.11.0) compile and run end-to-end: lean check PROVED honest LF2528 and CHEAT_REJECTED sorry_proof; dafny check PROVED DA0108_first_odd_scan and SPEC_TAMPERED assume_false. All 213 hermetic tests pass. 30 minutes. | ||||||
| 152 | little-coder | Runs | 96 / 100 | TypeScript | 2,737 | |
A harness optimized to smaller LLMs What the test found: little-coder v1.19.0 installs and runs: npm install succeeds (182 packages), all 715 vitest tests pass, 4/4 pytest RPC client tests pass, TypeScript typechecks cleanly, the CLI launcher starts pi and lists available models correctly. 4 minutes. | ||||||
| 153 | herdr-web-ui | Runs | 96 / 100 | TypeScript | 2,180 | |
Ovis (formerly herdr web UI): free, open-source browser and phone client for herdr. Chat and live terminal for Claude Code, Codex and every agent pane, remote... What the test found: The herdr-web-ui server starts, connects to herdr 0.9.5, answers health/session/access APIs with 200, and serves the built frontend via HTTP on port 7317. 8 minutes. | ||||||
| 154 | cloudroom | Runs | 96 / 100 | TypeScript | 1,825 | |
Cloud agents for any harness. Claude Code, Codex, Pi, and OpenCode run in isolated sandboxes, and live sessions move between your Mac and the cloud. What the test found: Cloudroom core v0.1.84 built from source, all 49 unit and integration tests pass, cargo fmt and clippy are clean, the HTTP API server starts and returns 200 on authenticated /v1/health. 28 minutes. | ||||||
| 155 | cloudroom-core | Runs | 96 / 100 | TypeScript | 1,825 | |
Cloud agents for any harness. Claude Code, Codex, Pi, and OpenCode run in isolated sandboxes, and live sessions move between your Mac and the cloud. What the test found: Cloudroom core built from source, passes fmt/clippy and all 31 Rust unit/integration tests, boots as a real HTTP service on loopback, and completed an authenticated session (start, prompt, recorded history, graceful restart/resume) against a local PostgreSQL 16 mock with both schema migrations applied. 33 minutes. | ||||||
| 156 | paperthin | Runs | 96 / 100 | JavaScript | 1,471 | |
The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering... What the test found: npm install succeeds with 14 packages (0 vulnerabilities). All 5 release gates (skills, catalog, links, prose, llms) pass. npm test runs 282 tests: 275 pass, 2 environment-specific failures (Codex quick_validate.py hash mismatch, npx resolution path) and 5 skipped. 12 minutes. | ||||||
| 157 | concord-mcp | Runs | 96 / 100 | TypeScript | 1,470 | |
Live messaging for coding agents What the test found: All 335 tests pass, the project builds cleanly, the concord CLI reports version 0.10.5, and the MCP server binary compiles without errors. 2 minutes. | ||||||
| 158 | paritok-4b-v1 | Runs | 96 / 100 | Python | 1,439 | |
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in... What the test found: Python package installed in a venv, the proxy serves on port 8088, answers /health (200) and /stats (200) and /v1/messages/count_tokens (200), and all 316 tests in the test suite pass. 8 minutes. | ||||||
| 159 | opentag | Runs | 96 / 100 | TypeScript | 1,432 | |
The open-source collaboration system for people and AI agents. Share context, coordinate tasks, and work in parallel with your team, cloud agents, Codex... What the test found: All 121 test files pass (1259 tests), typecheck passes, and the project builds cleanly with Node.js 22.14.0. 5 minutes. | ||||||
| 160 | opencode-telegram-bot | Runs | 96 / 100 | TypeScript | 1,370 | |
OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs locally on your machine. OpenCode V2 support. What the test found: The project installs, builds, typechecks, and lints cleanly with Node.js 22.14.0. The test suite passes 1969 of 1980 tests. All code-related tests pass, the 4 remaining failures are in e2e proxy connectivity tests that require IPv6 loopback, which is unavailable in this container. 16 minutes. | ||||||
| 161 | agent-deck | Runs | 96 / 100 | Go | 1,292 | |
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more. What the test found: Agent-deck vdev builds and runs in the container. The binary responds to version, help, and ls commands. 34 of 34 directly testable internal packages pass. The WebSocket terminal bridge functions correctly. Only pre-existing environment-specific test failures: keepalive client-count assertions (container PTY behavior)... 62 minutes. | ||||||
| 162 | building-a-coding-agent-from-scratch-course | Runs | 96 / 100 | Python | 1,237 | |
Learn harness engineering by building Claude Code from scratch. Free, open-source course: 8 articles, 6 videos, 1 codebase. What the test found: decode 0.1.0 is fully installed and functional: the CLI answers --version and --help, all 3078 executable tests pass (2998 unit + 80 integration), and all code-quality checks (format, lint, lockfile) pass cleanly with no errors. 4 minutes. | ||||||
| 163 | Mysti | Runs | 96 / 100 | TypeScript | 1,159 | |
AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate solutions, and synthesize the best approach for... What the test found: Mysti v0.4.0 installs, builds via webpack, and passes all 367 automated tests with vitest v2 on Node 18, with the vscode API mocked. 5 minutes. | ||||||
| 164 | opencode-manager | Runs | 96 / 100 | TypeScript | 1,107 | |
A self-hosted command center for OpenCode. Sessions, git, terminal, and schedules in one web app, from your phone or desktop. What the test found: All 3 packages (backend, frontend, CLI) build and all 5622 tests pass with coverage exceeding 80% thresholds across all categories. 22 minutes. | ||||||
| 165 | Free-LLM | Runs | 96 / 100 | JavaScript | 1,086 | |
74 free LLM API providers & 450+ free models (limits, no-card options) + Free-LLM Router: all of them behind one OpenAI/Anthropic-compatible endpoint with... What the test found: The Free-LLM Router starts, serves its dashboard and OpenAI-compatible API endpoint, and all 25 tests pass, covering authentication, failover, streaming, tool calls, embeddings, MCP, agent setup, and key security. 1 minute. | ||||||
| 166 | claude-code-memory-setup | Runs | 96 / 100 | Python | 1,075 | |
Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipeline. 🇧🇷... What the test found: All 6 CI checks pass (py_compile, ruff, JSON block validation, README parity, shellcheck), both Python scripts process real data producing correct Obsidian markdown with YAML frontmatter and auto-tags, the shell sync wrapper orchestrates the full pipeline, and the optional claude-conversation-extractor tool is... 5 minutes. | ||||||
| 167 | agentfiles | Runs | 96 / 100 | TypeScript | 865 | |
Browse, create, and edit AI agent files across Claude Code, Cursor, Codex, and 12 coding tools, from Obsidian. What the test found: In this container, the repo's full check gate passes: dependencies install cleanly with the frozen lockfile, the audit is clean, lint has 0 errors, all 24 tests pass, and the production esbuild build completes with no errors. 5 minutes. | ||||||
| 168 | CodeAF | Runs | 96 / 100 | Go | 825 | |
Open-Source Software factory for Open Models What the test found: codeaf v0.8.0 release binary installed, builds from source with SHELL=/bin/bash, all 31 law/test-quick packages pass, real model call to DeepSeek returns correct output. 31 minutes. | ||||||
| 169 | pi-extensions | Runs | 96 / 100 | TypeScript | 797 | |
A monorepo of Pi Coding Agent extensions (AI Slops) What the test found: npm install succeeds, npm test passes 5684/5686 tests, npm run check passes all typechecks and boundary checks, npm run format is clean, all on Node 22.23.3 with vitest 5.0.4. 50 minutes. | ||||||
| 170 | deer-workflow | Runs | 96 / 100 | TypeScript | 562 | |
An open-source graph engineering runtime that keeps orchestration in TypeScript and delegates semantic work to replaceable Agent runtimes. What the test found: The deer-workflow repository installs and builds cleanly with Bun 1.4.2, all 89 tests pass, and the CLI runs showing help for create/skill/run commands. 2 minutes. | ||||||
| 171 | procoder | Runs | 96 / 100 | Go | 212 | |
Senior-developer discipline for AI coding agents. A commit gate that counts unchecked as failing, quality controllers that refuse to call unfinished work done... What the test found: Procoder builds from source with Go 1.26.7 and its full Go test suite passes (57/57 packages), procoder test reports go pass, and the procoder binary runs version/help and its gate end-to-end, flagging conflict markers in a scratch repo. 7 minutes. | ||||||
| 172 | DSHA | Runs | 95 / 100 | Java | 3,651 | |
免 ROOT 免 Termux,在手机上跑 DeepSeek Harness。完整 Ubuntu 环境 + proroot 零 ptrace 开销 · AI 输出实时上屏 · ADB 直连 · 数据不丢 What the test found: Both Standard (Android 11+/arm64-v8a, 175 MB debug APK) and Low (Android 6+/arm64-v8a, 253 MB APK with Gecko) flavors build from source with all unit tests passing (619/0/0/0), all ELF binaries verified arm64-only with proper 16 KB page alignment and RELRO, and no foreign-architecture artifacts. 19 minutes. | ||||||
| 173 | Codync | Runs | 95 / 100 | Rust | 2,409 | |
Open source Grok Bot alternative, Bring your own agent and subscription: message Claude Code, Codex, Gemini CLI, Cursor, Copilot and 40+ AI agents as bots on... What the test found: codync-host 2.13.2 builds and serves HTTP on the configured port; all host unit/e2e tests pass; cloud and relay test suites pass fully; desktop app builds, typechecks, and passes 124/131 tests (7 SSH-related failures from missing /usr/bin/ssh in the container). 22 minutes. | ||||||
| 174 | zeroshot | Runs | 95 / 100 | Rust | 2,218 | |
Multi-agent graph harness for Claude Code, Codex and other coding agents. Separate agents review and test the work. Runs locally on your subscription. What the test found: Zeroshot installs via npm and builds from source; the CLI version, template list, UI server (200 on /ui/), and run validation all work, with 1607/1608 Rust tests passing in this container. 25 minutes. | ||||||
| 175 | ProjectAtlas | Runs | 95 / 100 | Rust | 514 | |
Every file not opened. Every folder not explored. Tokens saved. A local repository map for coding agents: purposes, source, symbols, and dependencies. Native... What the test found: ProjectAtlas builds from source with Rust 1.98.0, all 746 unit tests pass, 113 of 115 integration tests pass, CLI binary initializes and queries the repository. 36 minutes. | ||||||
| 176 | Codewhale | Runs | 94.7 / 100 | Rust | 41,197 | |
An open-source coding agent for your terminal, written in Rust. It works with any model, can split one task across several agents, and every line of it is... What the test found: Codewhale 0.9.11 builds, passes all tests, launches CLI help/doctor/exec against a mock API. Debug profile is memory-safe; release build hits OOM on constrained hardware. D-Bus dev headers were missing and were mocked via vendored crate sources. 42 minutes. | ||||||
| 177 | Vibe-Skills | Runs | 93.5 / 100 | Python | 3,837 | |
Intelligent Skill routing and workflow orchestration for AI agents, +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE. What the test found: VibeSkills v4.1.0 installs successfully, check verifies all 292 receipt-owned files, the vgo_cli Python launcher works end-to-end, and 129+ core unit tests pass with 3 isolated test failures due to missing pwsh in this container. 37 minutes. | ||||||
| 178 | gentle-ai | Runs | 93.3 / 100 | Go | 9,469 | |
Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven... What the test found: gentle-ai 2.0.0 builds from source, prints version (2.0.0-20260906031619-2c25e878eea4) and help text, all 53 Go test packages pass. 17 minutes. | ||||||
| 179 | cc-safety-net | Runs | 93.3 / 100 | TypeScript | 2,091 | |
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool... What the test found: The cc-safety-net project installs, builds, and runs its full test suite (3674 passing, 1 pre-existing failure). The built CLI binary answers version 2.4.6, the hook blocks destructive commands like 'git reset --hard', the explain command displays blocked verdicts, status and doctor produce reports, the API entry... 34 minutes. | ||||||
| 180 | svg-diagram | Runs | 93.3 / 100 | JavaScript | 676 | |
Agent skill that draws architecture, flowchart, sequence, data-flow and lifecycle diagrams as hand-placed SVG, to one linted house style. What the test found: With the patched test script, npm test passes 825/825 on the container's Node 18 and on Node 22, npm run lint:svg:all reports 11 files with 0 errors and 0 warnings, the skill installed into ~/.agents/skills/svg-diagram and runs from there, and the README's broken-SVG example reports the documented 3 errors/7 warnings... 5 minutes. | ||||||
| 181 | design.how | Runs | 93.3 / 100 | TypeScript | 622 | |
Design systems, skills and visuals for coding agents What the test found: All 278 self-test checks pass across 9 test suites (evals, oklch, check-system, capture-guard, pixdiff, land, bodies-check, legacy, parity), lint is clean for 8 skills, all 72 vault check scripts pass, Playwright with Chromium launches successfully, and all Python dependencies (fonttools, brotli, uharfbuzz, numpy... 12 minutes. | ||||||
| 182 | solo | Runs | 93.3 / 100 | Go | 605 | |
Solo Agent, an open-source, local-first workspace where humans and AI coding agents collaborate through channels, tasks, teams, and persistent memory. What the test found: In this container the Solo stack builds and runs on real PostgreSQL 16: server :8080 and paired daemon :8081 answer 200 on /readyz and /health, frontend :3000 serves the app, 81 migrations are applied, all Go unit tests pass, and 7 real end-to-end tests pass, while agent-powered onboarding waits on a logged-in LLM CLI... 56 minutes. | ||||||
| 183 | omg.dev | Runs | 93.3 / 100 | TypeScript | 560 | |
omg.dev, Remote control for claude, codex, cursor, opencode, pi, grok, jcode with mobile client What the test found: Dependencies installed, typecheck passes, the server starts on 127.0.0.1:8766 and all API endpoints respond correctly, and the test suite runs 5356 passing tests with only environment-specific failures related to Chromium, dbus, mobile native modules, and AI agent credentials. 38 minutes. | ||||||
| 184 | diri | Runs | 92 / 100 | Rust | 500 | |
The best way to work with coding agents. Run fifty in parallel, let them spawn each other, review everything in one place. What the test found: All headless Rust crates compile, pass clippy and fmt checks, and 114+691 tests pass; the diri-remote binary probes platform metadata and captures remote environments; the GPUI desktop app compiles through cargo check but cannot link in this 8GB container. 34 minutes. | ||||||
| 185 | openharness | Runs | 91 / 100 | TypeScript | 1,528 | |
The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and... What the test found: The CLI monorepo package installs, typechecks, builds, and passes all 5741 tests on Ubuntu 24.04 with Node 22.23.3, with sqlite3 and lsof made available in the container environment. 48 minutes. | ||||||
| 186 | 10x | Runs | 91 / 100 | TypeScript | 1,367 | |
⚡️ 10x - Up to 20x faster AI coding with multi-step Superpowers. Open-source agent with smart model routing, BYOK, fully self-hosted. What the test found: CLI help/version output works, web app returns HTTP 200 on /, 232 of 234 tests pass, and all 4 packages build cleanly; the 2 failing router tests need a real OpenRouter API key which the BYOK design requires. 4 minutes. | ||||||
| 187 | pydantic-deepagents | Runs | 91 / 100 | Python | 1,125 | |
Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams... What the test found: Package imports cleanly, CLI runs and reports version v0.3.43, 2771 of 2785 tests pass with pydantic-ai-backend pinned to v0.2.29. 25 minutes. | ||||||
| 188 | DeepCode | Runs | 90.7 / 100 | Python | 16,859 | |
"DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)" What the test found: The Python package is installed and builds, the CLI reports version 2.1.0, the app-server runtime probe passes, and the full test suite (1586 tests) passes. 3 minutes. | ||||||
| 189 | agent-toolkit | Runs | 90 / 100 | Python | 2,706 | |
A curated collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities across development... What the test found: Build system produces 56 valid plugin distributions. All session-handoff scripts work against real git projects. Manual skill install (cp -r skills/<name> ~/.claude/skills/) succeeds. The npx skills add quick install requires Node >=22 (container has v18); this is an environment limitation, not a repo defect. 2 minutes. | ||||||
| 190 | CodeNomad | Runs | 90 / 100 | TypeScript | 2,680 | |
CodeNomad: The command center that puts AI coding on steroids. What the test found: CodeNomad server builds, starts, serves its UI on port 9899 with working API endpoints; all typechecks pass; 3558/3593 tests pass (2 pre-existing failures unrelated to setup). Node 24.20.0 was required and manually provided. 39 minutes. | ||||||
| 191 | ripwire | Runs | 90 / 100 | C++ | 2,560 | |
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Cut agent token costs by finding code without reading the repo, then... What the test found: Build succeeds (plain dev build/ and Release build-install/), binary parses the repo source tree and emits deterministic minified XML with ranked symbols via Personalized PageRank, installed to /home/runner/.local/bin/ripwire with skills and hooks, --version/--help work, Python indexing confirms correct function... 21 minutes. | ||||||
| 192 | Aegis | Runs | 90 / 100 | Python | 1,453 | |
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks. What the test found: Aegis method pack installed and configured at /work/repo, aegis-doctor.py reports all 14 checks passing with ok:true, workspaceSupport:available, configStatus:configured; 218 core unit tests pass, 5 benchmark isolation tests fail only due to missing bwrap sandbox. 13 minutes. | ||||||
| 193 | commonly | Runs | 90 / 100 | JavaScript | 1,412 | |
Open-source workspace where your team and your agents share one pod. Connect the Claude Code or Codex you already run, @mention it next to your teammates, and... What the test found: Backend unit and service tests (60+ suites) all pass individually with in-memory MongoDB; frontend 112 suites/962 tests all pass; vite build succeeds; CLI responds with help; backend tsc compilation passes with 0 errors; full Docker stack not testable (Docker unavailable). 53 minutes. | ||||||
| 194 | phi | Runs | 90 / 100 | Go | 1,010 | |
A fast coding agent, rpc plugin, sub-agents, sloppy edits, and mcp What the test found: phi 16 MB binary builds from source, runs, and all tests pass on Go 1.26.9 linux/amd64. 2 minutes. | ||||||
| 195 | Async | Runs | 90 / 100 | TypeScript | 476 | |
IDE, A native-feeling AI coding workspace that blends chat, planning, agent execution, and project navigation into a unified desktop experience. What the test found: Dependencies installed; 709 of 709 tests pass; typecheck and the Vite renderer build succeed; the Async IDE desktop app starts on the virtual display, shows its main window, and keeps running past 6 minutes with auto-update disabled. 42 minutes. | ||||||
| 196 | claude-code-filetree | Runs | 90 / 100 | TypeScript | 475 | |
IDE-style file tree for Claude Code: a live pane that shows which files Claude reads and edits, with git status, diffs, content search, file previews and... What the test found: The repository type-checks with tsc --noEmit reporting zero errors; the claude plugin test harness runs 247 tests across 2 files (open.test.ts and surfaces.test.tsx) with all passing; CI convention checks (greps.sh, version-test.sh) pass; the standalone regex script confirms 241 translated ERE patterns agree with grep... 5 minutes. | ||||||
| 197 | JoySafeter | Runs | 90 / 100 | Python | 319 | |
🚀 JoySafeter: An enterprise AI Agent Platform, Not just chatting. building、running、testing, and tracing autonomous Agent Teams with visual orchestration... What the test found: Backend Python dependencies installed successfully, all 247 backend tests pass (1 expected skip). The test suite validates FastAPI routes, WebSocket handler, schema serialization, permissions, service layer, Pydantic adapter, prompt templating, and chat protocol parsing. 16 minutes. | ||||||
| 198 | heard | Runs | 89.3 / 100 | Python | 1,104 | |
Open-source (Apache 2.0) voice tool for Claude Code and Codex on macOS that reads your coding agent's progress aloud. The voice runs locally with Kokoro, no... What the test found: Heard Python package v1.1.48 installed and importable; CLI functional; 871/872 relevant tests pass on Linux (the 1 failure is macOS-specific afplay binary missing); ruff lint clean. 3 minutes. | ||||||
| 199 | no_human | Runs | 89.3 / 100 | Python | 323 | |
From ticket to reviewed pull request. Free and open-source, on your machine. What the test found: The no-human project (v0.2.0) is fully installed: uv sync completes, web board builds from source, the nh CLI responds with version 0.2.0, nh start binds and serves HTTP 200 in setup mode, the full node test suite (1584/1584) and the Python repoguard suite (142/142) pass. Task dispatch requires a Claude subscription... 71 minutes. | ||||||
| 200 | serena | Runs | 88 / 100 | Python | 31,607 | |
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent What the test found: Serena is installed, initialized, and the MCP server starts successfully with all 708 tests passing. 12 minutes. | ||||||
| 201 | MemoSync | Runs | 86.7 / 100 | TypeScript | 412 | |
Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex, Pi and OpenCode. What the test found: MemoSync 0.43.1 builds, installs, and serves its SPA on a local port with all three verified endpoints (/, /health, /api/v1/version) returning HTTP 200; the test suite reports 2243 passing and 10 environment-specific failures. 14 minutes. | ||||||
| 202 | claudexor | Runs | 86 / 100 | TypeScript | 525 | |
Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread... What the test found: pnpm install completed, pnpm build succeeded (31 packages in 18s), the CLI runs and reports version 3.9.8, the full test suite passes (350 test files, 4692 tests), canary stories pass (6 files, 50 tests), and typecheck passes (61 tasks). 20 minutes. | ||||||
| 203 | runjam | Runs | 85 / 100 | Rust | 221 | |
One desktop for all your AI coding Agent, Claude Code, Codex CLI & Gemini CLI. Auto-detect, one-click install, unified chat, file explorer, terminal & editor... What the test found: Frontend builds with Vite, backend compiles with Cargo, all 98 tests (13 JS + 85 Rust) pass, and the desktop binary launches on Xvfb and starts its proxy server. 16 minutes. | ||||||
| 204 | rtk | Runs | 80 / 100 | Rust | 87,495 | |
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies What the test found: RTK (Rust Token Killer) v0.42.4 builds from source, passes all 2936 tests with 0 failures, and runs as a working CLI proxy producing token-compressed filtered output for ls, git, cargo, and other commands. 8 minutes. | ||||||
| 205 | nightshift | Runs | 80 / 100 | Shell | 587 | |
Accountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results: a clear view of... What the test found: Nightshift v0.33.2 plugin for Codex is installed and enabled from the nightshift marketplace, with its 16 skills, runtime helpers (38+ verbs available via ns), hooks (hardhat, clock-out-gate, pulse, session-end, prompt-submit), and evidence system all operational as verified by 541+ passing bats test cases across 30+... 36 minutes. | ||||||
| 206 | agentplay | Runs | 80 / 100 | Python | 373 | |
Replay your coding agent sessions as a map and a timeline What the test found: Python package agentplay 0.2.2 installed from source, 991 tests pass, CLI builds sessions from Codex history and serves a functional web viewer with API returning available=true. 5 minutes. | ||||||
| 207 | thinkrail | Runs | 60 / 100 | TypeScript | 8,402 | |
ThinkRail is the agentic IDE that gets better every time you use it What the test found: 890 deps installed, 14 packages typecheck, 14/14 test suites pass (987 in server alone), web app builds, E2E 183/183 passes, server /health returns 200. 18 minutes. | ||||||
| 208 | ovis | Runs | 60 / 100 | TypeScript | 2,180 | |
Ovis (formerly herdr web UI): free, open-source browser and phone client for herdr. Chat and live terminal for Claude Code, Codex and every agent pane, remote... What the test found: Ovis builds, typechecks, and passes all 6161 unit tests. The server starts and listens on its configured port. No herdr daemon is available in this container, so integration tests requiring a live herdr session were not run. 4 minutes. | ||||||
| 209 | pi-mcp-adapter | Runs | 60 / 100 | TypeScript | 1,666 | |
Token-efficient MCP adapter for Pi coding agent What the test found: Installed and running on Node 22.23.3. Tests pass 1997/2000, typecheck passes, public exports verified, CLI works. 9 minutes. | ||||||
| 210 | zoetrope | Runs | 60 / 100 | Rust | 1,198 | |
Watch a Claude Code or Codex session as a live flow graph, in your terminal or your browser. What the test found: Zoetrope builds from source, passes all 216 tests, passes clippy and fmt checks, and the zoe binary reads and inspects both Claude and Codex session transcripts, outputting complete agent trees with tool counts and metadata. 4 minutes. | ||||||
| 211 | luvus | Runs | 60 / 100 | Rust | 1,016 | |
Mission control for your AI agents What the test found: luvus 0.14.2 builds successfully, the full locked test suite passes (2198/2198), the binary responds to --help, --version, doctor, and server status commands. One test assertion was relaxed to account for bracketed-paste wrapping in PTY panes, and Node 22 was installed for OMP extension TypeScript validation. 24 minutes. | ||||||
| 212 | sandboxd | Runs | 60 / 100 | Go | 1,001 | |
Open-source, self-hosted AI app builder, an agent builds real apps in isolated sandboxes on your own server, each live at a preview URL. Self-host in one... What the test found: Go 1.22.7 core test suite (23 packages) and console React/Vite unit test suite (33 tests) both pass; make build compiles sandboxd/runtimed Go binaries and bundles the console SPA; gofmt and go vet report no issues. 12 minutes. | ||||||
| 213 | pullboard | Runs | 60 / 100 | JavaScript | 850 | |
Autonomous development for real products. You set the standard. Declare your vision. Walk away. It builds. What the test found: Pullboard 0.9.0 is installed, the CLI answers commands, the view server binds a port, the spec check reports 0 errors, and the test suite passes 1410 of 1414 tests (1 container-specific parent-death runner test fails, 3 skip without Chrome). 59 minutes. | ||||||
| 214 | percho | Runs | 60 / 100 | TypeScript | 545 | |
Percho: Minimalist desktop GUI for the Pi coding agent, the same engine as the Pi CLI, in a clean visual interface. Multi-session chat, visual tool approvals... What the test found: All 538 tests pass across 49 test files in both packages/backend and packages/desktop; typecheck passes in all 3 workspaces; the production Electron build succeeds; the app launches and reports app ready v43.3.0. 8 minutes. | ||||||
| 215 | opencode-goal-plugin | Runs | 60 / 100 | TypeScript | 533 | |
OpenCode goal plugin for Codex-style goal mode, /goal slash commands, persistent objectives, and AI coding agent focus. What the test found: The repo installs cleanly from source: all dependencies resolve, TypeScript typechecks without errors, ESLint reports no violations, the full test suite (296 tests) passes, the server bundles to dist/server.js (206.6 KB), and npm pack --dry-run confirms the correct publish artifact (6 files, 284.4 KB unpacked). 2 minutes. | ||||||
| 216 | models | Runs | 60 / 100 | Rust | 523 | |
TUI and CLI for browsing models.dev, benchmarks, coding agents, and statuses for AI providers. What the test found: The modelsdev Rust project compiles, passes all 518 tests, and its CLI (help, version, list, agents status, status list, completions) produces correct output. 3 minutes. | ||||||
| 217 | ownmem | Runs | 60 / 100 | JavaScript | 428 | |
Open-source, Git-native memory for AI coding agents, deterministic local recall for Claude Code, Codex, Cursor, Gemini CLI, and compatible tools. What the test found: All ownmem tests (structure, public, and tokenizer) pass; benchmark achieves 100% Recall@1 with deterministic local retrieval; CLI help and init --preview both respond correctly. 2 minutes. | ||||||
| 218 | foremerge | Runs | 60 / 100 | Rust | 410 | |
Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git. What the test found: All 98 tests pass, both binaries (foremerge, fmg) report version 0.5.0, the query benchmark runs successfully, and the doctor command reports a healthy install with an uninitialized database (expected pre-init state). 3 minutes. | ||||||
| 219 | spellbook | Runs | 60 / 100 | Python | 300 | |
Cross-runtime skills for Claude Code, Codex, and multi-agent workflows. What the test found: 109 installable skills validated with 0 errors, install.sh installs 110 skills to ~/.agents/skills for Codex, and the full 532-test suite passes. 13 minutes. | ||||||
| 220 | agents | Runs | 56.7 / 100 | TypeScript | 1,652 | |
A durable process per agent, with memory that survives restarts What the test found: Node 22.19.0 with pnpm 9.15.0 installed, all dependencies resolved and built, type checks pass, boundary checks pass, 68 of 71 tests pass across packages/pi and packages/sandbox-adapter. 39 minutes. | ||||||
| 221 | alook | Runs | 56.7 / 100 | TypeScript | 1,530 | |
Multi-Agent Collaboration for Team and Friends What the test found: After upgrading to Node v22.14.0 and passing --experimental-require-module --experimental-websocket, all 7 testable packages typecheck and test cleanly (5,284 passing, 2 pre-existing failures from missing bun and a better-sqlite3/kysely adapter mismatch). 51 minutes. | ||||||
| 222 | tmux-ide | Runs | 56 / 100 | TypeScript | 569 | |
The open-source tmux GUI/TUI for your coding agents What the test found: tmux-ide in this repo builds and runs real tmux 3.7c sessions with send/ls/adopt/team, a 200-serving command-center REST+SSE API, a working control-socket send verb, and the full managed dev-instance lifecycle; 6618 daemon unit tests, 551 contract tests, 273 daemon-client tests, 1103 desktop-renderer tests, 70... 37 minutes. | ||||||
| 223 | jcode | Runs | 53.3 / 100 | Rust | 21,986 | |
High performance coding agent harness written in Rust, built for heavy multi-agent dev workflows What the test found: jcode v0.81.7-dev is built from source, installed via symlinks in ~/.jcode/builds/current and ~/.local/bin, and works correctly with OpenRouter provider. jcode run and jcode repl both complete successfully with real AI responses. 20 minutes. | ||||||
| 224 | pinvou-agent | Runs | 50 / 100 | Rust | 3,044 | |
Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables. What the test found: Vite frontend builds, 1436 JS tests pass, pinvou-knowledge Rust crate builds and its server serves API on port 3210 (200 OK), remote-control-relay passes 86/88 tests, architecture guard and fork guard both pass. 27 minutes. | ||||||
| 225 | compozy | Runs | 50 / 100 | Go | 2,902 | |
An operating system for AI agents. The autonomous control plane for your agents: see and steer every Claude Code, Codex, and Cursor session. Always-on agents... What the test found: CompozyOS builds from source, daemon runs and serves HTTP on port 2123 returning 200, Go tests pass across 19+ internal packages, and all 1029 frontend UI tests pass via vitest. 35 minutes. | ||||||
| 226 | delegate-skills | Runs | 50 / 100 | JavaScript | 2,651 | |
Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself, one per implementer. What the test found: The delegate-skills package installs all 18 skills, the test suite passes all checks against fake CLI shims, and the POSIX shim no longer depends on the external dirname command. 30 minutes. | ||||||
| 227 | moai-adk | Runs | 50 / 100 | Go | 1,259 | |
Agentic development harness for Claude Code, SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control... What the test found: moai-adk v3.1.3 builds and runs. Binary at ./bin/moai responds to 'moai version' with v3.1.3. Test suite runs with 3 pre-existing failures (2 test-isolation, 1 codex-binary not available). templ code generation works. All ast-grep rule tests pass with version 0.40.5. 57 minutes. | ||||||
| 228 | clawcodex | Runs | 50 / 100 | TypeScript | 928 | |
Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python. What the test found: Python virtual environment installs all dependencies cleanly, the 'clawcodex' CLI starts and reports version 1.6.0, and the full test suite of 10,435 tests passes with 0 failures. 51 minutes. | ||||||
| 229 | agnix | Runs | 50 / 100 | Rust | 494 | |
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plugin for all major IDEs included, with autofixes. What the test found: agnix 0.52.2 installed and working from both npm (user dir) and cargo source build; 4700+ tests passing across all 6 workspace crates; binary validates agent configs and produces text, JSON, SARIF, and GitHub annotations output formats with i18n support. 20 minutes. | ||||||
| 230 | cersei | Runs | 50 / 100 | Rust | 466 | |
The Rust SDK for building coding agents. Tools, streaming, graph, sub-agent orchestration, MCP, as composable functions What the test found: The 19-crate Rust workspace builds cleanly, all 612 tests pass, and the abstract-cli binary responds to --help and --version commands. 6 minutes. | ||||||
| 231 | cli-agent-orchestrator | Runs | 48 / 100 | Python | 1,629 | |
Multi-agent orchestration for AI coding CLIs, Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions What the test found: CAO server starts, responds 200 on /health and /docs, and passes all unit tests (2986+ passed) except for 4 pre-existing test-isolation wiki_lint failures and Node version-gated web UI build. 43 minutes. | ||||||
| 232 | lean-ctx | Runs | 40 / 100 | Rust | 3,957 | |
LeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence... What the test found: lean-ctx 3.10.1 release binary is built, installed at ~/.cargo/bin/lean-ctx, and fully functional with all CLI commands working. 65 minutes. | ||||||
| 233 | rea | Runs with mocks | 92 / 100 | TypeScript | 473,815 | |
Reverse engineer anything with agents, from app behavior down to native binaries. What the test found: npm ci installs 281 packages, tsc builds cleanly to dist/, and the full vitest suite runs 353 test files (1756 tests) with zero failures on Node 22.19.0. 7 minutes. | ||||||
| 234 | claude-context | Runs with mocks | 92 / 100 | TypeScript | 12,716 | |
Code search MCP for Claude Code. Make entire codebase the context for any coding agent. What the test found: Install, build, typecheck, lint config, and all 35 tests pass across the monorepo. The core indexing pipeline runs end-to-end with mock providers. The MCP server starts but requires real OpenAI API key and Milvus credentials for production use. 15 minutes. | ||||||
| 235 | grok-cli | Runs with mocks | 92 / 100 | TypeScript | 3,518 | |
An open-source coding agent for the Grok API What the test found: All 48 test files pass (248 tests), typecheck passes via tsc --noEmit, and CLI help displays correctly via bun run dist/index.js --help. 9 minutes. | ||||||
| 236 | tdd-guard | Runs with mocks | 92 / 100 | TypeScript | 2,386 | |
Automated TDD enforcement for Claude Code What the test found: TDD Guard installs, builds, and runs. All unit tests (770) and linter tests (24) pass. Core validation logic works with mock AI client. Jest, Vitest, Go, and pytest reporter integrations work. Validator integration and 6 language-specific reporter tests need real API credentials or additional language runtimes not... 53 minutes. | ||||||
| 237 | DemoGPT | Runs with mocks | 92 / 100 | Python | 1,905 | |
🤖 Create agentic apps in a second with your prompts. Everything you need to create an LLM Agent - tools, prompts, frameworks, and models - all in one place. What the test found: Install built a working venv with all dependencies. All 4 tests pass against a mock OpenAI server (2 LLM: OpenAIModel, OpenAIChatModel; 2 RAG: add_files, add_text). Streamlit app launches on port 8592 and returns HTTP 200. The demogpt CLI entry point uses subprocess('streamlit') which resolves only from the venv bin... 55 minutes. | ||||||
| 238 | Tianshu-harness | Runs with mocks | 92 / 100 | TypeScript | 1,365 | |
天枢harness是一个的终端编程智能体,它要回答的核心问题是:模型何以稳定地交付, 目标不漂移、完成有证据、验证有闭环,不说"应该修好了"。为此它在模型与真实世界之间建立一层认知执行环境(CVM),把目标、状态、证据、资源、权限与终止条件从对话历史中外部化,由运行时持续管理。同时对deepseek v4极度优化。 What the test found: The project builds from source (tsup bundle + native binary + staged runtime deps), the CLI binary launches and responds to --version, --help, sessions, and logs commands, and the test suite passes 99.9% of 19005 tests with one timing-dependent flaky failure. 19 minutes. | ||||||
| 239 | pi-from-scratch | Runs with mocks | 92 / 100 | TypeScript | 1,315 | |
600 行 TypeScript 写成的超级迷你版 pi,让你轻松从 0 写出属于你的 pi-agent What the test found: Repository installed, TypeScript compiles cleanly, all 25 unit tests pass, and the full agent loop (LLM stream → tool_call → tool execution → result injection → next turn) was exercised end-to-end against a mock OpenAI-compatible streaming API. 5 minutes. | ||||||
| 240 | MiniCode | Runs with mocks | 92 / 100 | TypeScript | 1,172 | |
A lightweight terminal coding assistant with Claude Code-like workflow, tool loop, and TUI architecture, built for learning and experimentation. Multi-language... What the test found: All 48 test suites (270 tests) pass. TypeScript compiles clean. Installer writes config and launcher correctly. App launches in both online and mock mode. 1 minute. | ||||||
| 241 | Whale | Runs with mocks | 92 / 100 | Go | 935 | |
Whale, blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, MCP tools, dynamic workflows. What the test found: Whale v0.0.0 builds from source with Go 1.26.8, all 53 test packages pass, the binary runs and reports its version, and CLI commands including help and exec function correctly (the latter returns the expected missing-API-key error). 3 minutes. | ||||||
| 242 | agy-staff | Runs with mocks | 92 / 100 | JavaScript | 909 | |
Hire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code, OpenAI Codex, and DeepSeek Harness. What the test found: Node v18.19.1, npm 9.2.0, project v0.9.1; skills generation passes; offline companion test suite passes 249/250 tests using fake AGY mock; real AGY binary not present so model-dependent features cannot be verified. 46 minutes. | ||||||
| 243 | HERO-Anti-OverDefense | Runs with mocks | 92 / 100 | Python | 889 | |
HERO = Hashing · Edge cases · Rubrics · Overbuild, the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code... What the test found: Goal Pulse Python script imports cleanly (goal_pulse module), all 18 behavioral and transport tests pass on Python 3.12.3 with websockets 15.0.1, and the CLI --help prints the 5 subcommands (start/status/stop/tick/run). 1 minute. | ||||||
| 244 | Pi-Bolt | Runs with mocks | 92 / 100 | TypeScript | 859 | |
⚡ Pi, the coding agent, compiled ahead of time to one native executable. 10× faster to start, 7× less CPU and 4.5× less memory than Pi on Node. Linux, macOS... What the test found: The Pi-Bolt monorepo installs, builds, and runs on Node.js v22.19.0. The CLI prints version 1.1.0. All script tests, TUI unit tests, AI core unit tests, and coding-agent unit tests pass. One pre-existing test expects a fireworks model that no longer exists in provider data. 15 minutes. | ||||||
| 245 | context-attachment-manager | Runs with mocks | 92 / 100 | TypeScript | 814 | |
Keep long, image-heavy Codex and Claude Code chats fast: earlier images become ID placeholders the model fetches back on demand, even after compaction. Local... What the test found: Node 24.22.3 installed via n. Codex plugin codex-attachment-manager@codex-attachment-manager v0.11.2 installed from local repo /work/repo via Codex CLI plugin marketplace. Engine running on port 17891 (PID 4461). Config.toml points Codex at localhost:17891/backend-api/codex. All 345 unit tests pass. 6 minutes. | ||||||
| 246 | Clean-Coder-AI | Runs with mocks | 92 / 100 | Python | 583 | |
✅2-in-1 AI Developer and Project Manager. AI agents plan an entire project in Todoist and code it task by task. What the test found: All unit tests pass (14/14), all 28 source modules import cleanly, main entry points (manager.py, single_task_coder.py) import without error, and Playwright Chromium browser is installed. 4 minutes. | ||||||
| 247 | pinloop-cli | Runs with mocks | 92 / 100 | TypeScript | 569 | |
Job board CLI for coding agents. Search and judge millions of worldwide postings from all white-collar sectors, refreshed hourly. What the test found: Pinloop CLI v0.8.2 builds from source with tsc, installs via npm, and runs 15 distinct commands (search, count, fetch, judge, pull, login, logout, account, viewed, guide, welcome, filter, billing, tab, message) against a mock API server returning realistic responses. 6 minutes. | ||||||
| 248 | apexyard | Runs with mocks | 92 / 100 | Shell | 553 | |
Your AI engineering org, governed. Ship agent-built code safely to production. What the test found: The repo's CLI tools (apexyard doctor, status) work, the hook test suite runner executes 335 tests, and 312+ pass after installing yq, pyyaml, gh stub, and an rsync wrapper; 5 environmental-only test failures remain due to missing gh CLI, single-commit git history, and Node 18 being too old for bpmnlint. 64 minutes. | ||||||
| 249 | facadecode | Runs with mocks | 92 / 100 | TypeScript | 515 | |
The multi-agent orchestrator for VS Code. Run Claude Code, Codex, and other agent CLIs that start, message, and operate each other across windows and machines. What the test found: Extension compiles, bundles, packages into a VSIX, and passes nearly all unit tests (2 cleanup timeout failures). IDE cannot install dependencies due to missing system library (kerberos/gssapi) unavailable without root. All extension operations verified with Node 24.22.2 on Linux x64. 32 minutes. | ||||||
| 250 | npcsh | Runs with mocks | 92 / 100 | Rust | 506 | |
the composable multi-agent shell What the test found: Python test suite passes (72/72), Rust test suite passes (8/8), Rust release binaries compile and respond to version and help, Python backend serves health endpoint, npcsh shell initializes and connects to the backend after a one-line migration SQL fix. 17 minutes. | ||||||
| 251 | pigo | Runs with mocks | 92 / 100 | Go | 503 | |
pi agent in Golang What the test found: pigo builds from source with Go 1.27.2; full test suite passes (1524/1524); the binary runs, and headless text, stream-json, session resume, the --no-tui REPL, and the full-screen TUI all executed a real agent loop against a schema-correct local mock Chat Completions endpoint, executing the bash tool and printing the... 21 minutes. | ||||||
| 252 | 10xProductivity | Runs with mocks | 92 / 100 | Python | 487 | |
Personal AI assistant for work inside corporate constraints, built on coding agents and the tools, sessions, and permissions you already have. What the test found: Python 3.12 venv installed the tenx-productivity editable package, the 16-test suite passes, and the slack-polling trigger host and stand-up prep CLI run end to end against a local schema-correct Slack mock, so the same binaries are ready for a real Slack token/cookie and a real coding-agent CLI once those credentials... 13 minutes. | ||||||
| 253 | HGM | Runs with mocks | 92 / 100 | Python | 449 | |
🧬 The Huxley-Gödel Machine What the test found: Python venv install is complete, all 22 repository tests pass, all main modules import, the real SWE-bench dataset and TestSpec construction were verified, and hgm.py boots through configuration/source-copy to its Docker-dependent self-improvement step, where execution stops because this container has no Docker daemon... 31 minutes. | ||||||
| 254 | metis | Runs with mocks | 92 / 100 | TypeScript | 444 | |
Metis is a coding agent that boosts AI/LLM coding performance by 50% QQ群: 801193315 What the test found: npm ci installs cleanly, npm run build produces working dist/, CLI prints version 1.4.0 and full help, 268 of 275 test files pass in non-root headless Electron environment. 34 minutes. | ||||||
| 255 | ai4j | Runs with mocks | 92 / 100 | Java | 442 | |
Java 8+ agentic SDK: unified LLM access (OpenAI/Anthropic/DashScope/Doubao/DeepSeek...),unified AI service(image/video/audio...), Tool Calling, MCP, RAG... What the test found: All 10 modules build, install, and pass their test suites (1624+ total tests, 0 failures, 10 skipped). The CLI JAR starts and responds to --help and extension list. The docs-site Docusaurus build requires Node.js >=20 (has 18.19.1) which is a preexisting constraint. 19 minutes. | ||||||
| 256 | youtube-tutorials | Runs with mocks | 92 / 100 | Python | 423 | |
All my YouTube tutorials. Everything here is free - but please follow me on YouTube if you find these helpful. What the test found: The full just check suite exits 0 with PATH containing casey/just, terraform, go, and uv binaries. 7 minutes. | ||||||
| 257 | robotics-agent-skills | Runs with mocks | 92 / 100 | Python | 405 | |
Agent skills that make AI coding assistants write production-grade robotics software. ROS1, ROS2, design patterns, SOLID principles, and testing, for Claude... What the test found: The install.sh installer installs skills to targets correctly, the skills validator reports 0 errors, and the with-skills demo_recorder eval package imports without ROS2 with its pytest suite running 16 passed and 12 ROS2-dependent skips, with a mock-driven node lifecycle saving a valid episode JSON. 10 minutes. | ||||||
| 258 | zot | Runs with mocks | 92 / 100 | Go | 371 | |
Yet another coding agent harness, lightweight and written in go. What the test found: zot 0.0.0 builds from source under a toolchain I installed, prints its version, launches its TUI, and ran a complete streaming agent conversation against my local OpenAI-compatible mock with exit 0, writing a session file; the full test suite passes 16/16 under -race when the container's injected OPENROUTER_API_KEY is... 22 minutes. | ||||||
| 259 | devbox | Runs with mocks | 92 / 100 | TypeScript | 342 | |
Open source autonomous engineering harness in your cloud. One sandbox per task, no real secrets inside. What the test found: All three component test suites (CLI 293/293, harness 1101/1101, helm chart 126/126) pass. Control-plane 1597/1608 pass; the 8 failures all require PostgreSQL 18 which is not available in this container. The CLI binary responds to its help command listing 10 commands. 8 minutes. | ||||||
| 260 | cheap-ag | Runs with mocks | 92 / 100 | TypeScript | 341 | |
50x your usage with cheap-ag. Opus/Astra plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitting limits. One MCP... What the test found: npm install, TypeScript build, and all 392 tests pass on Linux x86_64 with Node v22.23.4, using a compiled lsof replacement and no API keys. 7 minutes. | ||||||
| 261 | vibe-log-cli | Runs with mocks | 92 / 100 | TypeScript | 341 | |
A CLI tool for logging and analyzing Claude Code and Cursor ai-driven coding session. What the test found: The project installs, builds with tsup (ESM), passes all 839 tests, and the CLI binary prints its help text when launched with --help. 24 minutes. | ||||||
| 262 | sudocode | Runs with mocks | 92 / 100 | TypeScript | 296 | |
Lightweight agent orchestration dev tool that lives in your repo What the test found: CLI builds and all core commands work end-to-end for spec and issue management. Test runner (vitest) crashes with bus error on Node 18. Server fails to start due to ESM module resolution issues. Frontend has pre-existing TypeScript errors. Project requires Node >=20 for full compatibility. 36 minutes. | ||||||
| 263 | umadev | Runs with mocks | 92 / 100 | Rust | 267 | |
UmaDev: A coding agent that works like a real dev team, commanding the Claude Code / Codex / OpenCode you already use. What the test found: The Rust project builds, all 1466 unit/integration tests pass, the umadev binary runs and responds to --help, --version, doctor, init, and ci subcommands from a source build with no external API keys. 11 minutes. | ||||||
| 264 | jev-review | Runs with mocks | 92 / 100 | TypeScript | 254 | |
Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev. What the test found: The repo installs and builds with Node 20, its 13-test suite passes, the built dist/server.js is registered with the Codex CLI, and it serves an MCP jev_review call end-to-end against a local schema-valid Jev mock. 8 minutes. | ||||||
| 265 | agents | Runs with mocks | 92 / 100 | Python | 229 | |
Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents. What the test found: All 77 tests pass across 6 test files: agy_task_runner (25), grok_acp_task_runner (20), telegram_corpus (18), package_skill (7), update_readme_skills (6), and agent_runtime_sync (1). All scripts import cleanly. 2 minutes. | ||||||
| 266 | OpenAgentd | Runs with mocks | 92 / 100 | TypeScript | 217 | |
Open-source desktop app for a local coding agent. Watch every tool call, diff, and terminal command. Bring your own models; sessions stay on your machine. What the test found: The openagentd 2.26.0 backend server and web UI build cleanly, the suite passes 4728/4728 (12 skipped) plus 3168 web tests, the server answers 200 on /api/health/ready and /api/agents and /api/agents/registry, and a real chat turn completed against a local OpenAI-compatible mock, saving the assistant replies into the... 20 minutes. | ||||||
| 267 | ordewell | Runs with mocks | 92 / 100 | TypeScript | 212 | |
One goal becomes a plan graph you can edit; each task runs on its own agent (Claude Code, Codex, OpenCode, GitHub Copilot CLI and more), in parallel on its own... What the test found: Ordewell 0.14.5 installs and builds from source on Node 22; the core test suite passes 6692/6694 tests (2 pre-existing failures require Docker); the CLI reports version 0.14.5; the offline planner loop with mock provider passes all scenarios; bench data-dir tests pass 6/6; Node 18 is insufficient and must be upgraded... 74 minutes. | ||||||
| 268 | pitupitu | Runs with mocks | 92 / 100 | Rust | 208 | |
Talk to Claude Code and Codex by voice, from your phone, on any of your machines. The open-source box agent for pitupitu.chat; your agents run in herdr. What the test found: The box agent builds with all 91 tests passing, install.sh installed pitupitu 0.8.0 and herdr 0.9.5, and pitupitu connect dialed out with a valid protocol-5 hello and held the link, with the box starting a real herdr server. 8 minutes. | ||||||
| 269 | agav | Runs with mocks | 92 / 100 | TypeScript | 203 | |
Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI. What the test found: Agav v0.2.8 builds and runs successfully: CLI displays full help with all subcommands (run, agents, skills, sessions, mcp, workflows, job), version command returns '0.2.8', non-interactive mode processes prompts correctly using its built-in tools (read_file, list_directory, etc.), and 6615/6776 tests pass with all 55... 11 minutes. | ||||||
| 270 | hax | Runs with mocks | 90 / 100 | C | 1,006 | |
A minimalist, terminal-native coding agent written in C. What the test found: The project builds cleanly from source, all 121 tests pass (unit + e2e with mock provider), the binary responds to --help/--version and runs oneshot prompts with the mock provider. 2 minutes. | ||||||
| 271 | autoprompt-skill | Runs with mocks | 88.3 / 100 | JavaScript | 1,255 | |
Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks. What the test found: The autoprompt-skill v2.0.0 is installed globally with Node.js 20.20.2 and Python 3.12.3 with PyYAML and jsonschema. All 328 tests pass (534 with skips), 4 expected environment-specific failures remain (2 need bwrap, 1 needs @openai/codex, 1 is a pre-existing grok MCP test issue). 16 minutes. | ||||||
| 272 | talkcody | Runs with mocks | 87 / 100 | TypeScript | 480 | |
TalkCody - Code is cheap, show me your talk. 🚀 Free Open Source AI Coding Agent. What the test found: Bun/Node/Rust toolchain installed user-level; frontend builds and its 2845 tests plus 99 API tests pass against a local Turso mock; the API server answers 200 on /health and /api/remote-agents/configs; only the Tauri desktop binary could not be built because glib-2.0/webkit2gtk dev packages are missing and cannot be... 24 minutes. | ||||||
| 273 | HolyClaude | Runs with mocks | 86 / 100 | JavaScript | 2,680 | |
AI coding workstation: Claude Code + web UI + 8 AI CLIs + headless browser + 50+ tools What the test found: All 285 Node.js unit tests, 5 Python notification tests, and the CLI persistence shell test pass. Repository structure is validated end to end with product facts contracts, security policy, documentation, and patch scripts all verified. 2 minutes. | ||||||
| 274 | omnilogue | Runs with mocks | 86 / 100 | TypeScript | 2,336 | |
Desktop app and web server to browse, search and analyze your AI coding assistant history, Claude Code, Codex CLI, GitHub Copilot, Gemini CLI, Cursor, OpenCode... What the test found: TypeScript/React frontend builds and tests pass (>1450 tests, 0 failures); Vite Mock dev server serves app over HTTP; Rust/Tauri desktop backend cannot compile without GTK/WebKit system libraries (libwebkit2gtk-4.1-dev, libgtk-3-dev). 34 minutes. | ||||||
| 275 | deeptide | Runs with mocks | 86 / 100 | Rust | 1,112 | |
Built by DeepSeek, for DeepSeek, a Swift-native macOS coding agent What the test found: DeepTide Rust workspace builds, CLI runs in local-echo mode and against a mock OpenAI endpoint, all 1314 tests pass, GUI launches on virtual display, npm package entrypoint works under Bun. 10 minutes. | ||||||
| 276 | dscode | Runs with mocks | 86 / 100 | JavaScript | 1,002 | |
A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry What the test found: Install and setup complete, 570/586 unit tests pass, dscode exec mode works end-to-end with mocked LLM, TUI app needs real TTY: this is a headless-container limitation, the binary itself is healthy. 13 minutes. | ||||||
| 277 | nvx | Runs with mocks | 86 / 100 | Rust | 856 | |
Cross-Platform Micro-VM Sandbox for Agentic Workloads What the test found: Dependencies installed in a venv and the release bundle downloaded/verified; the Python tooling test suite passes (454 tests), OpenVMM runs its 4562-test unit suite with only the container's NUMA-seccomp-blocked mbind tests failing, the openvmm binary answers version/help, and the kernel plus all three initramfs... 78 minutes. | ||||||
| 278 | Linghun | Runs with mocks | 86 / 100 | TypeScript | 446 | |
AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification. What the test found: Install and build succeed CLI reports version 0 1 55 All commands render in help 6 of 13 failing test files fixed all remaining failures are pre-existing and confirmed in the original code. 74 minutes. | ||||||
| 279 | ospec | Runs with mocks | 86 / 100 | JavaScript | 391 | |
Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop, plan, act, verify, with durable specs and evidence in... What the test found: npm install completed without errors (Node 18 engine warnings only); ospec CLI v2.1.0 responds to --version, --help, init, status, change, session commands; release smoke test and content scan both pass; index rebuild tool works; global install via --prefix succeeds. 5 minutes. | ||||||
| 280 | Rapid-MLX | Runs with mocks | 85.3 / 100 | Python | 4,174 | |
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool... What the test found: Rapid-MLX 1.0.4 installed from source via uv; all non-MLX Python components functional on Linux x86_64; full inference requires Apple Silicon macOS. 23 minutes. | ||||||
| 281 | sno-station-skills | Runs with mocks | 85.3 / 100 | Shell | 870 | |
Sno: Smart agents. Senior habits. Better every day. Open-source skills that make Claude Code, Codex, Cursor and Hermes Agent work like a team that has shipped... What the test found: Sno Station v1.0.42 (skills v1.0.42) installed with sno 1.3.4 for Codex CLI; 41 skills deployed, all 39 skill self-tests pass; agent-to-agent mail and memory verified. 10 minutes. | ||||||
| 282 | elephant-goldfish-model | Runs with mocks | 82 / 100 | Python | 22,091 | |
Open-source plugin for designing and reviewing software with agents What the test found: All 49 unit tests pass across 6 test modules: frontmatter validation, link integrity, harness/plugin manifests, scenario coverage, skill load limits, and Claude trace directory parsing. 1 minute. | ||||||
| 283 | SWE-ReX | Runs with mocks | 82 / 100 | Python | 655 | |
Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more. What the test found: Package installs cleanly, 74 tests pass, server binary starts and responds correctly on all core endpoints (is_alive, create_session, execute), CLI --version prints 1.4.0. 23 minutes. | ||||||
| 284 | devvm | Runs with mocks | 72 / 100 | Go | 750 | |
One VM for every project. An isolated sandbox with your project’s toolchain, ready for you or a coding agent to start coding What the test found: devvm builds from source and runs on Linux x86_64 with Go 1.27.3; all 35 Go unit-test packages pass, CLI tests pass, 46 of 48 testscript integration tests pass (2 fail due to missing ssh-keygen and nc); binary reports version 0.0.0 and lists 34 commands via --help; doctor reports expected missing runtime deps (Lima... 35 minutes. | ||||||
| 285 | humanize | Runs with mocks | 72 / 100 | Python | 428 | |
The agent flow system for token maxxing. What the test found: The hmz package installs cleanly, ruff lint passes, the CLI binary prints valid usage output, and 2600+ unit tests + 145+ integration tests pass against mocked backends; 11 unit test failures are pre-existing environment constraints (Landlock, argv0 path) unrelated to install. 25 minutes. | ||||||
| 286 | splash | Runs with mocks | 71 / 100 | C++ | 2,627 | |
A local inference engine for Apple silicon, built around the model. What the test found: Python server components (installer, launcher, model catalog, HTTP server, API protocol, images, documents, chat templates, constraints, tools, tokenization, crash tracing) pass ~1031 tests on Linux. Native Metal inference engine requires macOS 26.4+ Apple Silicon and Xcode. 34 minutes. | ||||||
| 287 | chainloop | Runs with mocks | 71 / 100 | Go | 615 | |
Agentic SDLC infrastructure. Define guardrails. Collect signals. Enforce continuously. Signed records of what your AI coding agents and CI/CD pipelines did... What the test found: Chainloop CLI and both server components (controlplane, artifact-cas) compile and install. 71 of 76 test suites pass. The 5 failing suites require Docker/testcontainers which is unavailable. The installed CLI binary responds to --help and version commands. 16 minutes. | ||||||
| 288 | openqodex | Runs with mocks | 56 / 100 | TypeScript | 1,198 | |
Open source AI code review for coding agents. A separate reviewer checks every change your agent writes before you push, in Claude Code, Codex, Cursor and... What the test found: With Node 22.20.0 and pnpm 9.15.4 under $HOME/opt: install and build are clean, the CLI launches and reports 0.8.1, init installs working agent files, scan runs 8 real scanners and reports the demo's 22 planted findings, unit and e2e suites pass fully except two documented environment-version cases (git 2.43 vs 2.44... 13 minutes. | ||||||
| 289 | cuga-agent | Runs with mocks | 56 / 100 | Python | 1,194 | |
CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable... What the test found: CUGA 0.4.1 installs successfully with uv, imports cleanly, and 2358 of 2362 unit tests pass with a dummy OPENAI_API_KEY; 3 test_sdk_citations failures are ordering-dependent and pass when run in isolation. 29 minutes. | ||||||
| 290 | ref-tools-mcp | Runs with mocks | 56 / 100 | TypeScript | 1,186 | |
Helping coding agents never make mistakes working with public or private libraries without wasting the context window. What the test found: After npm install, npm run build, and npm run check all succeeded, the app builds to an executable dist/index.cjs; the HTTP server answered 200 'pong' on /ping and a full MCP session (initialize, tools/list, tools/call search/read, prompts) returned 200 with correct results against a mock Ref API, while the stdio... 3 minutes. | ||||||
| 291 | SWE-AF | Runs with mocks | 56 / 100 | Go | 1,137 | |
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship. What the test found: The swe-af package is installed in the venv, all 1317 tests pass, and python -m swe_af starts a uvicorn server on port 8001 (reports degraded mode because no AgentField control plane is running on localhost:9999). 14 minutes. | ||||||
| 292 | poirot | Runs with mocks | 56 / 100 | Python | 261 | |
Poirot is a deep research agent kernel built for those who care about how agents are architected. What the test found: poirot installs via pip into a venv, all 2716 unit/integration tests pass, and the CLI binary reports help for run and cli subcommands. 30 minutes. | ||||||
| 293 | ouroboros | Runs with mocks | 44.3 / 100 | Python | 6,382 | |
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes... What the test found: All unit tests pass (0 failures in ~21000 tests across 34 unit directories), ruff lint and format clean, CLI boots with correct version, MCP server help displays correctly, 2 Windows-specific bugs were caught and fixed. 73 minutes. | ||||||
| 294 | openinterpreter | Runs with mocks | 30.7 / 100 | Rust | 68,941 | |
A coding agent for open models like Kimi K3.1 and GLM 5.3 What the test found: The codex-rs workspace builds successfully, the binary launches, and the core protocols/config/otel/api tests all pass. CLI tests pass at 99.4% with only 2 pre-existing failures unrelated to the installation: features list doesn't fetch cloud config, and sandbox enforcement needs bubblewrap. 71 minutes. | ||||||
| 295 | nWave | Could not verify | 80 / 100 | Python | 637 | |
AI agents that guide you from idea to working code, with you in control at every step. What the test found: nwave-ai v3.22.2 installed in a venv, deploys to ~/.claude/ for Codex CLI, all 10 doctor checks pass, 34 agents and 151 skills install successfully, and all key Python modules (nwave_ai.cli, des.domain, nwave_ai.sync, nwave_ai.outcomes) import without errors. 7 minutes. | ||||||
| 296 | harmonyos-ai-skill | Could not verify | 80 / 100 | Shell | 293 | |
鸿蒙(HarmonyOS NEXT)开发知识包,一份源文件自动产出 Claude Code / Cursor / Copilot / Codex / Gemini CLI / Windsurf / ChatGPT 等 11+ AI 工具的配置文件,让 AI 像熟读华为文档的工程师一样帮你写 ArkTS / ArkUI。 What the test found: Build pipeline produces 29 dist files for 11+ AI tool formats from harmonyos-development/SKILL.md (4461 lines, 65 sections). All validation and frontmatter checks pass. Claude Code skill symlinked at ~/.claude/skills/harmonyos-development. 10 minutes. | ||||||
| 297 | fence | Could not verify | 50 / 100 | Go | 1,025 | |
Lightweight, container-free sandbox for running commands with network and filesystem restrictions What the test found: could not be verified; the log shows where it stopped. 10 minutes. | ||||||
| 298 | agentty | Could not verify | 50 / 100 | C++ | 560 | |
AI pair programming in your terminal, one static binary, sub-ms startup, any model What the test found: Prebuilt agentty 0.9.26 linux x86_64 release binary is installed at /home/runner/.local/bin/agentty and responds to all query subcommands (version, status, config doctor, skills, help, diagnostics). Source build fails at the jaal submodule due to insufficient compiler support for C++26 structured binding packs. 30 minutes. | ||||||
| 299 | router | Could not verify | 40 / 100 | Go | 5,622 | |
Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change. What the test found: could not be verified; the log shows where it stopped. 14 minutes. | ||||||
| 300 | Codewhale | Could not verify | 20 / 100 | Rust | 41,197 | |
An open-source coding agent for your terminal, written in Rust. It works with any model, can split one task across several agents, and every line of it is... What the test found: could not be verified; the log shows where it stopped. 19 minutes. | ||||||
| 301 | agent-orchestrator | Could not verify | 20 / 100 | TypeScript | 15,015 | |
Plan, run and supervise fleets of agents from task to merged PR. Desktop (macOS, Windows, Linux) + iPhone & Android apps. Supports Claude Code, Codex & 35+... What the test found: could not be verified; the log shows where it stopped. | ||||||
| 302 | scrawl | Could not verify | 20 / 100 | Rust | 948 | |
Show an agent a problem: mark up, record, send What the test found: could not be verified; the log shows where it stopped. 47 minutes. | ||||||
| 303 | bug-hunter | Could not verify | 20 / 100 | JavaScript | 572 | |
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more... What the test found: could not be verified; the log shows where it stopped. | ||||||
| 304 | agentty | Could not verify | 20 / 100 | C++ | 560 | |
AI pair programming in your terminal, one static binary, sub-ms startup, any model What the test found: could not be verified; the log shows where it stopped. 7 minutes. | ||||||
| 305 | machinist | Could not verify | 20 / 100 | Go | 542 | |
Open source software factory infrastructure for advanced AI coding workflows What the test found: could not be verified; the log shows where it stopped. | ||||||
| 306 | orca-agent | Could not verify | 20 / 100 | Rust | 520 | |
Orca Agent, a DeepSeek-native terminal coding agent What the test found: could not be verified; the log shows where it stopped. | ||||||
| 307 | spec-kitty | Could not verify | 10 / 100 | Python | 1,737 | |
Spec-Driven Development with organizational governance. Specs tell AI agents what to build; Charter governs how they build it. Git-native missions, enforceable... What the test found: could not be verified; the log shows where it stopped. 87 minutes. | ||||||
| 308 | kapitsa | Could not verify | 10 / 100 | C++ | 857 | |
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai What the test found: 9 Python-only tests pass, but the Kapitsa C++ project cannot be configured, built, or run on this x86_64 Linux container, it requires macOS 14+ with Apple Silicon (arm64), Objective-C++, and Metal GPU framework. 3 minutes. | ||||||
| 309 | cli | Could not verify | 10 / 100 | Rust | 701 | |
AI coding agent for your terminal, with C/C++ build, debug, sanitizer and profiling tools. A fork of OpenAI Codex CLI. What the test found: could not be verified; the log shows where it stopped. 87 minutes. | ||||||
| - | deepx-code | Not yet verified | - | Go | 394 | - |
| - | exact | Not yet verified | - | Rust | 4,907 | - |
| - | munder-difflin | Not yet tested | - | TypeScript | 9,693 | - |
| - | atlas | Not yet tested | - | TypeScript | 9,183 | - |
| - | zeron | Not yet tested | - | Rust | 3,731 | - |
| - | superdesign-skill | Not yet tested | - | JavaScript | 1,047 | - |
| - | sno-station | Not yet tested | - | TypeScript | 1,026 | - |
| - | squadra | Not yet tested | - | Python | 981 | - |
| - | copperhead | Not yet tested | - | TypeScript | 706 | - |
| - | birdview | Not yet tested | - | TypeScript | 704 | - |
| - | Locals | Not yet tested | - | Python | 665 | - |
| - | alphacode | Not yet tested | - | Rust | 649 | - |
| - | octomind | Not yet tested | - | Rust | 647 | - |
| - | pi-dynamic-workflows | Not yet tested | - | TypeScript | 595 | - |
| - | Dodaios | Not yet tested | - | Python | 452 | - |
| - | cc-sessions-viewer | Not yet tested | - | Rust | 421 | - |
| - | OpenLore | Not yet tested | - | TypeScript | 368 | - |
| - | genie | Not yet tested | - | TypeScript | 354 | - |
| - | devo | Not yet tested | - | Rust | 347 | - |
| - | llmtrim | Not yet tested | - | Rust | 276 | - |
| - | mulmoterminal | Not yet tested | - | TypeScript | 276 | - |
| - | code-cli | Not yet tested | - | TypeScript | 219 | - |
| - | uncut | Not yet tested | - | Go | 103 | - |
runs installed and started with its real dependencies. runs with mocks started after stand-ins replaced external services such as a database or a third-party API. could not verify neither the standard agent nor the stronger one got it running within the time limit; the log shows where it stopped.
How we tested
On this list as of the latest test: 232 projects ran as-is, 62 with mocks, 15 could not be verified, 23 still waiting. Languages tested: C, C++, Go, Java, JavaScript, Python, Rust, Shell, TypeScript. Every attempt used a clean single-use machine, the subject at a pinned version, and a 90-minute limit for standard projects; the complete procedure is on the methodology page.
Frequently asked questions (FAQs)
How is this list ranked?
By measurement, not opinion: projects Argusic installed and launched on a fresh machine come first, then those that ran with mocks in place of external services, then those it could not verify. Ties go to the Argusic Score, then how popular it is on its own source.
Why are some projects unranked?
23 projects are still waiting for a test or for a finished attempt. They are listed without a rank until Argusic has measured them.
Where is the evidence?
Every row links to the project's Argusic page, where each run has a full log and a terminal recording stored with a sha256 fingerprint. The same pages exist for every one of the tested projects, on this list or not.
More lists in this category
- developer CLI tools (shares ANUS, Codewhale, CoreCoder, DeepSeek-Reasonix, MiniCode, abacusai-bot, agent-deck, agentacct, agentbox, agentty, agentty, alphacode, autoprompt-skill, brain.md, cc-safety-net, claudexor, cli, codeAgent, codealmanac, compozy, copperhead, crit, dao-code, dscode, easy-agent, foremerge, herdr, herdr-reviewr, jcode, jevgrep, lazyskills, octomind, oh-my-agent, ospec, ouroboros, pullboard, rea, ripwire, rtk, runner, sqz, tuios, zero, zero, zeroshot with this list)
- AI agent frameworks (shares CORAL, DeepSeek-Reasonix, EnterpriseAgentFramework, Vibe-Skills, agent-orchestrator, agentic-os, agents, commonly, elephant-goldfish-model, gentle-ai, harnessrouter, herdr, munder-difflin, oh-my-claudecode, omnigent, openharness, pi-rust, pydantic-deepagents, rea, zot with this list)
- self-hosted AI apps (shares OpenAgentd, agentfiles, atlas, claude-code-memory-setup, commonly, crit, harnessrouter, open-cowork, opencode-manager, ouroboros, parallel-code, sandboxd, thinkrail, twinny with this list)
- MCP servers (shares cli-agent-orchestrator, commonly, concord-mcp, ffmpeg-skill, gentle-ai, lean-ctx, memorix, okf-agent-memory, ouroboros, pi-mcp-adapter, rea, ripwire, serena, squadra with this list)
- workflow automation tools (shares 10xProductivity, Linghun, Vibe-Skills, autoprompt-skill, lazyskills, metis, pinvou-agent, smart-ralph with this list)
- LLM gateways (shares EnterpriseAgentFramework, Free-LLM, casbin-gateway, paritok-4b-v1, router with this list)
- browser automation tools (shares HolyClaude, dsh-browser, pi-desktop, wmux with this list)
- project management tools (shares CodeKanban, nimbalyst, vibe-log-cli with this list)
- open source video editors (shares Orkas-VideoStudio, ffmpeg-skill, openfilm with this list)
- wikis (shares brain.md, codealmanac, stash with this list)
- code editors (shares Async, Async with this list)
- observability tools (shares agentacct, zoetrope with this list)
- speech tools (shares heard, qwen-audio-agent with this list)
- vector databases (shares ai4j, claude-context with this list)
- self-hosted git servers (shares atlas, opencode-manager with this list)
- CI/CD tools (shares kelos with this list)
- screen recorders (shares scrawl with this list)
- API clients
- API gateways
- CMS platforms
- VPN tools
- backup tools
- Open source databases, installed and queried
- e-commerce platforms
- ebook readers
- game engines
- open source games
- home automation tools
- low-code platforms
- map tools
- message queues
- Open source music servers, installed and played
- Open source office suites, installed and launched
- self-hosted password managers
- search engines
- self-hosted analytics
- static site generators
- uptime monitors
- video players
- web scraping tools
- whiteboard tools
- self-hosted Notion alternatives
- self-hosted dashboards