Open source AI agent frameworks, installed and run
AI agent frameworks you can run yourself. The list is ordered by whether each project came up when Argusic installed it fresh, with the recording of that attempt one click away.
Tested between and . Each row shows its own test date; a project can change after that day.
187 of 193 tested projects run. 12 more waiting for a test.
In short: 148 of the 193 tested projects started as-is on a fresh machine: taste-skill, deer-flow, ai-job-search, anything-llm, herdr, CowAgent, oh-my-claudecode, and ai-website-cloner-template, and 140 more. 39 more started once a stand-in replaced a service they expect, such as a database: rea, mem0, marketingskills, DeepTutor, nanobot, Claude-Code-Game-Studios, Jobs_Applier_AI_Agent_AIHawk, and artemis, and 31 more. 6 could not be verified: openclacky, OpenBot, agent-orchestrator, astrid, AgenticX, and skillhub; 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 | taste-skill | Runs | 100 / 100 | JavaScript | 120,013 | |
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages What the test found: install.sh symlinks all 14 skills into ~/.codex/skills, skill.sh resolves skill names to SKILL.md paths, draw.mjs deals art directions from a library of 247 curated sites, lint.mjs scans source files for banned patterns, and all 5 unit tests in tests/skill_test.sh pass. 3 minutes. | ||||||
| 2 | deer-flow | Runs | 100 / 100 | Python | 85,610 | |
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message... What the test found: Backend Gateway boots and serves health checks on port 8003 (HTTP 200), 1642 backend tests pass, 160 blocking-IO tests pass, 24811 frontend unit tests pass, all dependencies installed. 62 minutes. | ||||||
| 3 | ai-job-search | Runs | 100 / 100 | Python | 73,013 | |
The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep... What the test found: Python test suite (321 unittest tests) and all 6 Bun portal CLI test suites (231 tests) pass. LinkedIn search CLI makes live queries and returns results. 4 Python analysis tools (security_guards, framework_version, lint_skills, verify_pdf) run successfully. 8 minutes. | ||||||
| 4 | anything-llm | Runs | 100 / 100 | JavaScript | 68,514 | |
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience What the test found: The AnythingLLM monorepo installs and builds cleanly; the server boots on port 3001 responding to API calls; the collector boots on port 8888; all 1,119 unit tests across server (725) and collector (394) pass without errors. 20 minutes. | ||||||
| 5 | 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. | ||||||
| 6 | CowAgent | Runs | 100 / 100 | Python | 48,044 | |
Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model... What the test found: CowAgent 2.1.9 installs, builds, all 1949 tests pass, web console binds on 127.0.0.1 and answers /api/health with 200 OK, and the CLI reports version 2.1.9. 17 minutes. | ||||||
| 7 | 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. | ||||||
| 8 | ai-website-cloner-template | Runs | 100 / 100 | TypeScript | 39,625 | |
Clone any website with one command using AI coding agents What the test found: Next.js 16.3.0 project builds, typechecks, and serves HTTP 200 on the root route via npm run dev. 4 minutes. | ||||||
| 9 | book-to-skill | Runs | 100 / 100 | Python | 38,736 | |
Turn any technical book PDF into a Claude Code skill, ready to study, reference, and use while you work. What the test found: The book-to-skill package is installed as an editable pip package, passes ruff lint, all 627 tests pass, skill validation passes, and the CLI extracts text from documents producing structured JSON metadata and clean text output. 3 minutes. | ||||||
| 10 | 9router | Runs | 100 / 100 | JavaScript | 32,740 | |
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40%... What the test found: Root npm install completed, npm run build succeeded, the standalone Next.js app serves the login page (200), models API (200 with JSON model list), and version endpoint (200), and the test suite runs 2562 passing tests. 42 minutes. | ||||||
| 11 | haystack | Runs | 100 / 100 | Python | 27,076 | |
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with... What the test found: Haystack 3.3.0-rc0 installed with Hatch, all 6569 unit tests pass, package builds to sdist and wheel. 4 minutes. | ||||||
| 12 | agent-desktop | Runs | 100 / 100 | Rust | 26,114 | |
Computer use CLI for AI agents What the test found: npm-installed and source-built agent-desktop 1.1.0 both answer version with ok:true, its 4311 Rust tests pass with 0 failures, and against a real GTK3 app on Xvfb+openbox with the real at-spi2-registryd, snapshot, find, get, click, and screenshot all work, where clicking the Go button changed the button's accessible... 62 minutes. | ||||||
| 13 | img2threejs | Runs | 100 / 100 | Python | 21,764 | |
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D. What the test found: All 1416 forge test suite tests pass. forge/ state.py, next.py, report.py, stage2_spec/validate_sculpt_spec.py, stage3_build/generate_threejs_factory.py all import and run cleanly from Python 3.12 stdlib. 7 minutes. | ||||||
| 14 | lemo-opuscar | Runs | 100 / 100 | JavaScript | 19,824 | |
A toolbox of film styles made in code for Claude Code: 99 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by... What the test found: With Node 20.20.2, the core, voice, and music installs exit 0, and the real pipeline produced a 6.000-second 1920x1080 24 fps film with 144 H.264 frames and stereo AAC audio that fully decoded with exit 0. 7 minutes. | ||||||
| 15 | xerj | Runs | 100 / 100 | Rust | 19,394 | |
AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search... What the test found: XERJ v1.0.0-rc.77 built from source in 2m06s (quick profile), serving ES-compat API on :9200 with autoindex and MCP server working; test suites pass except 2 IPv6 bind failures specific to this container. 36 minutes. | ||||||
| 16 | openfang | Runs | 100 / 100 | Rust | 18,275 | |
Open-source Agent Operating System What the test found: OpenFang 0.6.9 compiles, passes 2699 tests, and the daemon starts successfully, booting 30 agents and serving the API on port 4200 with a health endpoint returning HTTP 200. 28 minutes. | ||||||
| 17 | vibe-coding-cn | Runs | 100 / 100 | Makefile | 17,755 | |
Vibe Coding 非严肃开发的从入门到门入的工具箱 What the test found: All repository quality gates pass except check-research-raw which requires gh CLI auth. Node v22 and Python venv with all dependencies are installed from /tmp. Submodules initialized. Markdown lint and all Python-based checks (links, details, structure, directory coverage, metadata, AI citations, external resources... 6 minutes. | ||||||
| 18 | Octop | Runs | 100 / 100 | Python | 12,335 | |
A smarter, self-hosted AI assistant, multi-user, multi-agent. What the test found: Python dependencies installed and resolved, 3401 unit tests pass, `octop --version` prints v1.0.2b5, `octop run` starts uvicorn listening on the configured port, and the health endpoint ('/api/health') returns 200. 16 minutes. | ||||||
| 19 | cocoindex | Runs | 100 / 100 | Rust | 11,927 | |
Incremental engine for long horizon agents 🌟 Star if you like it! What the test found: The Python package builds and installs from source, the CLI runs and prints version 999.0.0, 1095 Python tests pass (core engine, ops, resources, connectors that don't need external services), and 144 Rust tests pass across the core, utils, and SDK crates. 12 minutes. | ||||||
| 20 | loop-engineering | Runs | 100 / 100 | TypeScript | 11,820 | |
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani... What the test found: Both documented CLIs build and run from a clean copy, 252 validation-gate tests pass with 0 failures, and the repository audits at 100/100 L2. 10 minutes. | ||||||
| 21 | Graft | Runs | 100 / 100 | TypeScript | 11,443 | |
One shared memory for every coding agent on your team. Claude Code, Cursor and Codex get a map of your code and your team's past decisions, so they pick up... What the test found: npm install completes, TypeScript compiles, the CLI builds/checks/queries a structural code graph on a real repo without any keys, and all 1220 tests run with 0 failures. 10 minutes. | ||||||
| 22 | Trail-Code | Runs | 100 / 100 | TypeScript | 11,443 | |
One shared memory for every coding agent on your team. Claude Code, Cursor and Codex get a map of your code and your team's past decisions, so they pick up... What the test found: The graft CLI installs, builds, and its full test suite passes (1491/1492, 1 deliberate skip) with both previously-failing shim-resolution and lock-release tests green, and the CLI builds/parses/queries a scratch repo and completes an LLM deep pass against a local mock endpoint. 87 minutes. | ||||||
| 23 | pixel-agents | Runs | 100 / 100 | TypeScript | 10,334 | |
A playful way to manage your AI workforce What the test found: Pixel Agents builds from source, passes all 1501 tests, and the standalone CLI server starts on localhost responding HTTP 200 on both / and /api/health. 5 minutes. | ||||||
| 24 | mobilerun | Runs | 100 / 100 | Python | 10,093 | |
Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖 What the test found: Mobilerun 0.6.19 is installed in a Python 3.12 venv. All 979 tests pass (0 failures). The CLI responds to --version and --help. The package imports cleanly. Anthropic SDK is pinned to 1.17.0 for MessageParam compatibility. 45 minutes. | ||||||
| 25 | openbrowser | Runs | 100 / 100 | TypeScript | 9,594 | |
Let AI agents browse the web. An autonomous toolkit for browser-based AI agents. What the test found: The open-browser monorepo installs cleanly with bun, all 364 core tests pass, the CLI prints help and opens URLs in a headless Playwright Chromium browser, and the library can navigate, screenshot, and extract markdown from real web pages. 6 minutes. | ||||||
| 26 | ccpm | Runs | 100 / 100 | Shell | 8,462 | |
Project management skill system for Agents that uses GitHub Issues and Git worktrees for parallel agent execution. What the test found: CCPM skill is installed at ~/.codex/skills/ccpm with its SKILL.md, 6 reference docs (conventions, execute, plan, structure, sync, track), and 14 deterministic bash scripts. All 14 scripts execute without errors in both populated and empty project states, producing correctly formatted status reports, standup summaries... 2 minutes. | ||||||
| 27 | steel-browser | Runs | 100 / 100 | TypeScript | 7,999 | |
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about... What the test found: With a user-local Node 22 and Chrome for Testing plus DISABLE_CHROME_SANDBOX=true, the dev-mode API runs on port 3000, /v1/health returns 200 with live Chrome, and sessions/scrape/screenshot/pdf plus external CDP client connections all worked with real results. 11 minutes. | ||||||
| 28 | opengap | Runs | 100 / 100 | TypeScript | 3,191 | |
A framework-agnostic, git-native standard for defining AI agents What the test found: The OpenGAP CLI builds from source with npm install && npm run build, all 51 tests pass, and all CLI commands (version, validate, export, init, info, audit, skills) execute correctly. 2 minutes. | ||||||
| 29 | waku-agent | Runs | 100 / 100 | Python | 2,213 | |
Waku Agent is an open-source AI agent harness you own: loop, memory, evals, and an always-on layer (event inbox, timers, approvals, outbox), in code that stays... What the test found: Waku is fully installed at /work/repo/.venv. The dashboard serves HTTP 200 on localhost:7777. All 1714 deterministic evals pass offline. Ruff lint passes. The CLI (waku --help, waku connections, interactive waku) works correctly. 6 minutes. | ||||||
| 30 | harmonist | Runs | 100 / 100 | Python | 2,100 | |
Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies. What the test found: Harmonist pack v1.2.3 is fully integrated into /work/repo: pack health 19/19, verify integration 22/22, smoke test 7/7, hooks 79/79, memory 41/41, cross-platform 17/17, all 21 script test suites passing. 9 minutes. | ||||||
| 31 | agentic_security | Runs | 100 / 100 | Python | 2,048 | |
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪 What the test found: The agentic-security package installs on Python 3.12, the CLI --help displays usage, the FastAPI health endpoint returns 200, the CI scan command runs successfully against a local self-probe endpoint, and 390 of 390 selected tests pass with zero failures. 6 minutes. | ||||||
| 32 | trpc-agent-go | Runs | 100 / 100 | Go | 1,940 | |
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability. What the test found: The tRPC-Agent-Go framework compiles and all 235 test suites pass under Go 1.21, the E2E tests pass under Go 1.24.4, and examples compile successfully under Go 1.24.4. 25 minutes. | ||||||
| 33 | jido | Runs | 100 / 100 | Elixir | 1,919 | |
🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows. What the test found: The Jido 2.3.3 Elixir project compiles clean and all 2470 non-flaky tests pass on OTP 27.3.4.1 / Elixir 1.18.1-otp-27, covering agents, AgentServer, signals, directives, state ops, plugins, sensors, scheduling, storage, threads, and orchestration. 11 minutes. | ||||||
| 34 | bub | Runs | 100 / 100 | Python | 1,704 | |
Bub it. Build it. A tiny agent runtime, composable with plugins. What the test found: Dependencies installed via uv sync, all 579 tests pass, ruff lint and mypy type-check pass with no issues, bub CLI displays all commands, and the chat REPL launches successfully. 2 minutes. | ||||||
| 35 | Agently | Runs | 100 / 100 | Python | 1,673 | |
[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and... What the test found: Agently 4.1.4.8 installs and runs from a Python virtual environment; 2736 tests pass covering Agent execution, Actions, TaskBoard, TriggerFlow, Shell, RecordStore, Skills, Code execution, structured output, long-output continuation, compatibility registry, and context contracts. 16 minutes. | ||||||
| 36 | better-agents | Runs | 100 / 100 | TypeScript | 1,562 | |
Standards for building agents, better What the test found: pnpm build succeeds via esbuild + tsc; test suite passes 15 tests, 36 todo/skipped; CLI works end-to-end generating proper project scaffolding including .env with API keys, AGENTS.md, .mcp.json, src/, tests/, and prompts/. 6 minutes. | ||||||
| 37 | chidori | Runs | 100 / 100 | Rust | 1,372 | |
The agent framework where every run is durable, replayable, and resumable by default. What the test found: chidori 3.8.1 builds and runs: CLI run/serve/resume/verify/check all operational, Rust test suite 537/539 pass, Python SDK 29/29 tests pass, HTTP health endpoint returns 200, record-replay durability verified with byte-identical replay. 17 minutes. | ||||||
| 38 | 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. | ||||||
| 39 | 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. | ||||||
| 40 | MasterAgent | Runs | 100 / 100 | C++ | 967 | |
Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency. What the test found: All 6 ctest suites pass with 100% pass rate; all 5 eval binaries report all tests/checks passed; no errors encountered during build or test execution. 2 minutes. | ||||||
| 41 | Foundry | Runs | 100 / 100 | Python | 896 | |
The foundation layer for agentic intelligence. What the test found: promptise CLI returns version 0.1.dev1, all 7 commands (list-tools, run, agent, validate, init, serve, runtime) listed via --help, and 3314 tests collect and pass across all unit, server, orchestration, runtime, identity, and e2e test suites without integration markers. 33 minutes. | ||||||
| 42 | semantix | Runs | 100 / 100 | Go | 815 | |
semantic agent kernel which make agent efficient and self-evolve What the test found: The Semantix project compiles fully from source, all 3 binaries (semantix, semantix-agent, semantix-gateway) are built and runnable, 143 of 143 test packages pass (1 pre-existing flaky fuzz test in harness/agent fails intermittently under parallelism), and basic functional operations (extract, search, doctor) work... 26 minutes. | ||||||
| 43 | aeon | Runs | 100 / 100 | JavaScript | 797 | |
The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops... What the test found: All 4 apps install cleanly and pass typecheck. Dashboard tests (205/205) and webhook tests (7/7) all pass. CLI binary responds correctly. Only the Next.js dashboard build fails due to Node 18 vs >=20 requirement. 7 minutes. | ||||||
| 44 | crabtalk | Runs | 100 / 100 | Rust | 738 | |
The long-running embedded agent What the test found: The repo compiles, all 25 tests pass, and the crabtalkd daemon starts and accepts CLI commands (crabtalk ps, version, info) over a Unix domain socket with no third-party credentials required. 10 minutes. | ||||||
| 45 | mnemon | Runs | 100 / 100 | Go | 733 | |
LLM-supervised persistent memory for AI agents, graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw... What the test found: All 19 deterministic Go test packages pass, the mnemon binary builds and runs, and the installed binary at $GOBIN/mnemon successfully executes memory operations (remember, recall, status) on a real SQLite-backed store. 5 minutes. | ||||||
| 46 | swarmclaw | Runs | 100 / 100 | TypeScript | 712 | |
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM... What the test found: SwarmClaw installs, builds, passes all 938 tests, and runs: the built and dev servers both answer 200 on /api/healthz, the web app serves HTML on /, the CLI answers --help and version 1.9.40, and the Electron desktop app launches on the virtual display and loads its UI. 9 minutes. | ||||||
| 47 | agentos | Runs | 100 / 100 | TypeScript | 691 | |
TypeScript AI agent framework: cognitive memory, dynamic personalities, emergent behaviors and self-building designs What the test found: AgentOS 0.10.19 builds from source with pnpm install, TypeScript compiles to dist/, and 2100+ vitest tests pass across config, memory, API, runtime, orchestration, RAG, e2e, and cognition modules on Node.js 18.19.1 with better-sqlite3 and hnswlib-node native addons rebuilt manually. 54 minutes. | ||||||
| 48 | daydreams | Runs | 100 / 100 | TypeScript | 628 | |
Daydreams is a set of tools for building agents for commerce What the test found: pnpm install succeeds, all 13 packages build, 157/157 core tests pass, core module imports cleanly with 20+ exported symbols. 6 minutes. | ||||||
| 49 | deerflow-book | Runs | 100 / 100 | JavaScript | 595 | |
本书围绕 DeerFlow 2.0,从理论到源码,系统讲解如何进行二次开发。(精校) What the test found: The VitePress documentation site for the DeerFlow 二次开发 book installs, builds (0 errors, 18 chapter pages), and serves via vitepress dev on port 5173. 2 minutes. | ||||||
| 50 | forall-mcp | Runs | 100 / 100 | Rust | 496 | |
Forall (∀) is a coding harness from Astrio that helps developers build correct software by generating spec-driven code alongside machine-checkable proofs. What the test found: Rust workspace builds with cargo, all 44 unit/integration tests pass, and the npm MCP bridge correctly proxies MCP tool requests between stdio and Streamable HTTP. 5 minutes. | ||||||
| 51 | AutoHarness | Runs | 100 / 100 | Python | 470 | |
AutoHarness: Automated Harness Engineering for AI Agents What the test found: The AutoHarness CLI and library install and build cleanly in a project venv, the governance pipeline runs for real (validation, allowed/denied tool calls, mode switching, wrap, export, claude-code hook install), and the full test suite passes 958/958; the only mocks needed are LLM credentials for the AgentLoop. 5 minutes. | ||||||
| 52 | Hypha | Runs | 100 / 100 | TypeScript | 452 | |
Harness-oriented agent system framework for production-grade LLM agent applications What the test found: Hypha builds and runs: the API server serves 200 on /api/v1/status/page, /api/v1/status, /api/v1/openapi.json and completes governed tool executions with verified hashes, and the unit (305), package (2420), integration (44), and native production-topology acceptance (6) tests all pass against locally stood-up MongoDB... 36 minutes. | ||||||
| 53 | flowcraft | Runs | 100 / 100 | Go | 410 | |
Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice, runnable as a library, a daemon, or a real-time pipeline. What the test found: All 7 Go workspace modules pass vet and tests, and the forge demo binary prints its command usage. 6 minutes. | ||||||
| 54 | pydantic-ai-skills | Runs | 100 / 100 | Python | 382 | |
This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills. What the test found: pydantic-ai-skills works against the current pydantic-ai-harness line: the package installs, all 351 tests pass, and a real agent run loads a bundled skill, reads a reference file, and executes its script, with Git and S3 registries syncing libraries harness accepts. 49 minutes. | ||||||
| 55 | yoagent | Runs | 100 / 100 | Rust | 380 | |
The agent loop for Rust, stream from 7 LLM protocols, run tools, loop until done. From a laptop to a Cloudflare Worker. What the test found: yoagent v0.23.0 compiles and its full test suite passes with zero failures on Rust 1.99.1 using only crate-bundled dependencies and MockProvider-based tests. 13 minutes. | ||||||
| 56 | AI-company | Runs | 100 / 100 | Python | 379 | |
Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured... What the test found: AI Team OS v1.14.0 API answers 200 on /api/health, serves 187 REST endpoints and 116 MCP tools. Codex adapter installed with 7/7 hook files, MCP via stdio verified. SQLite database at ~/.claude/data/ai-team-os/aiteam.db holds 47 tables with working project/task CRUD and cross-request persistence. Unit tests pass... 44 minutes. | ||||||
| 57 | Cortico | Runs | 100 / 100 | TypeScript | 379 | |
Event-stream AI Agent framework for building your persona bot 🍊 What the test found: pnpm install completes, pnpm test runs 4908 tests all passing, pnpm run typecheck passes cleanly, pnpm start launches the bot with a web console responding on port 7788 with no auth required. 11 minutes. | ||||||
| 58 | tinystruct | Runs | 100 / 100 | Java | 365 | |
A lightweight, modular Java application framework for web and CLI development, designed for AI integration and plugin-based architecture... What the test found: tinystruct 1.7.37 framework compiles from source, all 408 tests pass (0 failures), CLI dispatcher correctly routes actions, and the built-in HTTP server on port 8080 responds with 200 on GET /?q=say/*. 17 minutes. | ||||||
| 59 | aft | Runs | 100 / 100 | Rust | 348 | |
Give your agent a proper IDE and OS. The sensorimotor cortex for coding agents (OpenCode + Pi), part of CortexKit: symbol-aware edits, semantic search, code... What the test found: AFT v0.58.0 builds from source with Rust and TypeScript. The Rust binary (aft) receives JSON-over-stdio commands and responds to version queries. All 3957 Rust unit tests pass. TypeScript plugin build produces working dist bundles. All Pi plugin tests pass (839). OpenCode plugin tests: 1566 pass, 3 are... 55 minutes. | ||||||
| 60 | whatsapp-ai-agent-sdk | Runs | 100 / 100 | TypeScript | 322 | |
The open-source AI agent SDK for WhatsApp. Bring your own model, your own number, your own data. Local-first, no forced cloud, no vendor lock-in. What the test found: The full npm workspace builds (tsc), passes typecheck (tsc --noEmit), and passes all 1,202 tests across 9 packages with 0 failures after upgrading to Node 22 and adding the missing rolldown optional native binding. 2 minutes. | ||||||
| 61 | agentao | Runs | 100 / 100 | Python | 314 | |
Local-first, governed AI agent runtime for Python, embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in. What the test found: Agentao 0.5.7.dev0 installs, builds, and passes its entire 6336-test suite inside the container with mock credentials; real LLM chat requires a genuine API key. 6 minutes. | ||||||
| 62 | Libra | Runs | 100 / 100 | Python | 311 | |
Libra: Efficient Resource Management for Agentic RL Post-Training What the test found: Full install succeeded, 303/303 test suite tests pass, 6 skipped, and 2 of 3 broken example scripts now run end-to-end on CPU-only container with no GPU required. 28 minutes. | ||||||
| 63 | 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. | ||||||
| 64 | animaworks | Runs | 100 / 100 | Python | 268 | |
Organization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama). What the test found: 17092 unit tests pass; CLI prints full help; demo server binds port 18501 with Uvicorn; all 5 pre-existing test failures fixed via IPv6 loopback detection, zstd Python fallback, and Node 18 ESM compatibility. 44 minutes. | ||||||
| 65 | awesome-ai-agents-2026 | Runs | 100 / 100 | Python | 250 | |
🤖 A curated list of AI Agent frameworks, tools, platforms, and resources for 2026, the year agents went mainstream What the test found: All Python maintenance scripts and the 10-test unittest suite pass cleanly; the network link check over 1210 URLs exited 0 with 0 confirmed-dead links, the only non-200 results being 75 access-blocked and 5 transport-error URLs that the repository explicitly classifies as unverified rather than broken. 2 minutes. | ||||||
| 66 | KADATH | Runs | 100 / 100 | Python | 250 | |
Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimization of a goal. What the test found: KADATH Python package installed and all 53 test cases pass using the fixture specialist model (no external credentials). Kernel lifecycle (init, approve, run, status, export) verified end-to-end. CLI binary responds with usage help. 4 minutes. | ||||||
| 67 | 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. | ||||||
| 68 | skills-constitution | Runs | 100 / 100 | Python | 236 | |
Skills Constitution, meta-rule governing all skill invocations across agent platforms What the test found: Skills Constitution v2.31.0 installs and all 142 regression tests pass. The skill tree (764 standalone + 326 plugin skills) loads, the pre-hook injects context correctly, the constitution-gate blocks/protects as designed, and the workbuddy/cursor/prompt install modes copy files and rebuild the tree without error. 5 minutes. | ||||||
| 69 | agentdescent | Runs | 100 / 100 | Python | 221 | |
Gradient descent, but the parameters are agents, a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the... What the test found: agentdescent 0.8.0 installed in venv. CLI works (demo, --help, --version). All 6559 tests pass deterministically offline with no API keys. 70 minutes. | ||||||
| 70 | centra-gideon-agent | Runs | 100 / 100 | Python | 207 | |
The companion AI agent that learns, adapts and gets the work done no matter the task What the test found: From a clean checkout the standard install steps succeed on this container after user-level Rust and Node 22 installs; the gateway boots, serves the console and authenticated API, and the built Hypermid daemon answers real memory-record create and list requests. 47 minutes. | ||||||
| 71 | dspy-go | Runs | 100 / 100 | Go | 205 | |
DSPy Go implementation What the test found: DSPy-Go library and CLI build successfully, all 35 test packages pass, CLI responds to list/describe/version/help commands. 9 minutes. | ||||||
| 72 | mozaik-network | Runs | 100 / 100 | TypeScript | 203 | |
The communication network for AI agents. What the test found: The Mozaik Network server starts on port 3000, serves REST API endpoints (create/list networks, create peers, create/revoke invites) and WebSocket connections for peer messaging; all 47 automated tests pass covering HTTP endpoints, WebSocket messaging, peer join/leave/reconnect, invite-based access, metering, and the... 3 minutes. | ||||||
| 73 | Trend2Video-Pro | Runs | 100 / 100 | Python | 131 | |
Trend-to-Video Agent Framework for publish-ready short video packages What the test found: Trend2Video Pro installed, all 11 tests pass, CLI generation produces valid MP4 with full publish package (title, description, hashtags, subtitles, thumbnail, metadata, quality report), API responds on /health and /api/score endpoints, benchmark runs, and SQLite database stores topics and generation history. 6 minutes. | ||||||
| 74 | Trend2Video-Pro | Runs | 100 / 100 | Python | 131 | |
Trend-to-Video Agent Framework for publish-ready short video packages What the test found: A fresh install runs all 13 tests, the API returns 200 on its documented endpoints, the Streamlit UI generates a package, and the CLI produces a decodable 30-second 1080x1920 MP4 with 48 valid subtitle cues. 14 minutes. | ||||||
| 75 | 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. | ||||||
| 76 | plandex | Runs | 98.7 / 100 | Go | 15,931 | |
Open source AI coding agent. Designed for large projects and real world tasks. What the test found: Plandex server starts on port 8099 with PostgreSQL 16.4 and LiteLLM proxy on port 4000; server tests pass; CLI builds and authenticates against local server; full CRUD API for projects, plans, branches, settings is operational. 18 minutes. | ||||||
| 77 | ponytail | Runs | 98 / 100 | JavaScript | 196,773 | |
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. What the test found: All 110 tests pass: the root project's behavioral, plugin, correctness, and hardware-awareness tests (84), the Pi extension's mode/injection tests (23), and the MCP server's instruction-building tests (3) all succeed. 3 minutes. | ||||||
| 78 | invisible_dots | Runs | 98 / 100 | TypeScript | 58 | |
invisible dots: open-source, self-hosted alternative to OpenAI Dots, Grok Bot. Built to be undetectable by anti-bot systems. What the test found: npm ci installed 428 packages, the CLI bundle and web client built, npm run typecheck passed, npx vitest run gave 2103 passed/3 skipped and go test gave 120 passed after I fixed the secret-input backspace bug and the execEnv DISPLAY bug, and the control plane served HTTP 200 on /api/health, /api/dots and the web UI... 22 minutes. | ||||||
| 79 | khazix-skills | Runs | 97.5 / 100 | Python | 22,460 | |
数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader(帮你定义目标), neat-freak 洁癖, hv-analysis, khazix-writer & more, Claude Code, Codex & 40+ agents What the test found: AIHOT v2.0.0 installed and its live endpoints returned 200, neat-freak's structural suite passed 11 behavior and 21 trigger cases, the PDF converter produced a readable 2-page Chinese PDF, and the storage report server served 200 while rejecting an out-of-allowlist delete with 403; Linux disk scanning returned... 5 minutes. | ||||||
| 80 | 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. | ||||||
| 81 | Douyin_TikTok_Download_API | Runs | 97.3 / 100 | Python | 21,518 | |
🚀 自托管的抖音、TikTok、B 站数据采集与无水印视频下载 API,支持 AI agent 通过 MCP 调用与离线语音转文字,Docker 一键部署。| Self-hosted TikTok, Douyin & Bilibili scraper and no-watermark video... What the test found: All 2960 tests pass (2450 unit + 510 integration), the CLI outputs version 5.0.1 and lists 10 commands, the API server starts and serves healthz/readyz/swagger/console root with 200, the web console SPA is built, and both the PostgreSQL+TimescaleDB and Redis backends and the Go downloader sidecar run. 48 minutes. | ||||||
| 82 | 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. | ||||||
| 83 | Yuxi | Runs | 97.3 / 100 | Python | 7,720 | |
可私有部署的多租户知识智能体平台:统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and... What the test found: Backend Python dependencies installed and locked; all 1640 backend unit tests pass; all 164 web unit tests pass; Vite production build completes successfully; engineering trust contracts and lint checks pass. Two minor test permission-assertion bugs fixed (umask compatibility) and one Node.js version gap resolved... 25 minutes. | ||||||
| 84 | ragflow | Runs | 96 / 100 | Go | 94,538 | |
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure. What the test found: Python 3.13 venv with 697 deps installed, Go toolchain auto-resolved to go1.27, C++ librag_tokenizer_c_api.a built with clang++-20, Go binaries ragflow_server and ragflow-cli compiled successfully, Go unit tests pass (all packages), Python unit tests pass (5145/5145), frontend builds successfully, native static libs... 40 minutes. | ||||||
| 85 | dsh-our-free-model | Runs | 96 / 100 | JavaScript | 83,892 | |
在 dsh 里装上这个插件即可,无需登录、注册或填 API Key,就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型, 完全免费,不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API... What the test found: Node 22.23.3 installed via n; npm install added 21 dev packages; tsc --noEmit passed; all 31 test suites pass; host-selftest confirmed the plugin activates, serves model picker with 26 free models + 1 region-limited, performs plain chat, tool calling, effort budgets, vision, and OpenAI-compatible forwarding against... 16 minutes. | ||||||
| 86 | ai-job-search | Runs | 96 / 100 | Python | 73,014 | |
The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep... What the test found: Python test suite passes (805/805), all 6 portal CLI test suites pass (495/495), CV and cover letter compile to verified PDFs with lualatex/xelatex, and live job searches return real data from Danish and global job portals. 14 minutes. | ||||||
| 87 | 500-AI-Agents-Projects | Runs | 96 / 100 | Python | 40,529 | |
The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to... What the test found: Web app builds with vite and serves HTTP 200 on port 5173. All 3 CrewAI MCP course lessons execute end-to-end with OpenRouter. SQL query agent creates demo database and answers natural language questions. Unit test generator agent produces passing 21/21 pytest suites. News summarizer falls back to mock data and... 12 minutes. | ||||||
| 88 | claude-code-templates | Runs | 96 / 100 | Python | 34,101 | |
Open-source registry and CLI for Claude Code components: agents, commands, skills, hooks, MCPs, settings and mods What the test found: The claude-code-templates CLI tool installs, builds, and passes all 22 test suites (233 tests) via Jest plus 13 node:test tests. The CLI binary responds to --help, --version, --health-check, and removed-flag diagnostics. Dependencies are installed and the test suite validates version synchronization, external skill... 35 minutes. | ||||||
| 89 | Jobs_Applier_AI_Agent | Runs | 96 / 100 | Python | 32,611 | |
AIHawk: AI job application bot, automated job search, job hunting, auto-apply to resume-matching jobs while you sleep. What the test found: All 211 tests pass and the CLI responds correctly to --help and --version. The project is ready for use with an OrcaRouter API key. 3 minutes. | ||||||
| 90 | nanoclaw | Runs | 96 / 100 | TypeScript | 31,145 | |
Your own always-on AI assistant: self-hosted, open source, lightweight. Each agent runs in its own container on your machine, on the harness you choose (Claude... What the test found: The NanoClaw project installs, compiles with tsc, passes typecheck with tsc --noEmit, and all 2945 host tests pass via vitest. 10 minutes. | ||||||
| 91 | page-agent | Runs | 96 / 100 | TypeScript | 29,734 | |
JavaScript in-page GUI agent. Control web interfaces with natural language. What the test found: Install, sequential build, typecheck, lint, and all 69 unit tests pass. The project is fully functional with Node v22. via nvm. 27 minutes. | ||||||
| 92 | distilly | Runs | 96 / 100 | Python | 26,777 | |
Distilly, Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill(原同事 Skill). What the test found: The full test suite passes (73/73, plus 9 subtests), the Node.js CLI installs the distilly skill to any target path, and every Python tool in tools/ prints correct usage on --help. 2 minutes. | ||||||
| 93 | awesome-claude-code-subagents | Runs | 96 / 100 | Shell | 26,725 | |
A collection of 100+ specialized Claude Code subagents covering a wide range of development use cases What the test found: The repository clone is complete: 161 agent definitions with valid YAML frontmatter across 10 categories, a syntax-valid interactive installer (needs TTY), a fully operational subagent-catalog CLI skill with 12-hour TTL cache and fetch/search/list/invalidate commands, and all documentation (README, CONTRIBUTING... 5 minutes. | ||||||
| 94 | dolt | Runs | 96 / 100 | Go | 24,959 | |
Dolt, Git for Data What the test found: Built dolt 2.3.5 from source: 'dolt version' prints 2.3.5, CLI sql/log/diff work, sql-server answered MySQL clients on TCP (create db, create tables, query, commit, branch, merge, history), and push/clone/pull over a file:// remote completed, with only the gpg-dependent unit test failing due to the absent system gpg... 37 minutes. | ||||||
| 95 | agent-framework | Runs | 96 / 100 | Python | 14,720 | |
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET. What the test found: Python Agent Framework installs and its entire test suite passes across core, tools, providers (OpenAI, Anthropic, Gemini, Ollama, Mistral, Bedrock, Foundry), orchestrations, declarative, A2A, hosting, Redis, ChatKit, GitHub Copilot, and AG-UI packages. 28 minutes. | ||||||
| 96 | QuantDinger | Runs | 96 / 100 | Python | 13,910 | |
The most complete open-source, self-hosted Agentic Trading OS, AI research, Python strategies, factor discovery, backtesting, optimization, paper/live... What the test found: QuantDinger Python API v5.4.1 is installed and fully functional, all 3050 unit tests pass, the Flask app creates and serves the health endpoint on HTTP 200, and the only skipped tests require PostgreSQL/integration Docker containers that are not available in this environment. 7 minutes. | ||||||
| 97 | claude-skills | Runs | 96 / 100 | JavaScript | 12,485 | |
67 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer. What the test found: python3 scripts/validate-skills.py passes with 0 errors, make test runs 12/12 passing, and the site builds 99 static pages successfully via Node 20. 6 minutes. | ||||||
| 98 | voltagent | Runs | 96 / 100 | TypeScript | 11,001 | |
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework What the test found: Monorepo builds (29/29 packages), lints (0 errors, 5 warnings), and all 25 packages with runnable unit tests pass (~2776 tests). The only test failure is @voltagent/e2e which requires an unreachable PostgreSQL database. Two test files with a pre-existing ESM dependency conflict are excluded. 26 minutes. | ||||||
| 99 | PraisonAI | Runs | 96 / 100 | Python | 9,380 | |
Private AI agents for highly regulated teams, and for anyone who wants AI on their own computer. Open-source Python agent framework that runs fully offline. What the test found: PraisonAI Python SDK core (praisonaiagents v1.7.8) and wrapper (PraisonAI v4.7.10) installed from source with all 9 sub-packages, 898 Python unit tests pass across both packages, CLI responds with version 4.7.10, TS SDK (v1.7.4) builds and 146/158 test suites pass (2521/2659 tests). 26 minutes. | ||||||
| 100 | mcp-agent | Runs | 96 / 100 | Python | 8,591 | |
Build effective agents using Model Context Protocol and simple workflow patterns What the test found: uv sync installs cleanly, the CLI binary reports version 0.2.6, the test suite achieves 1500/1505 passing (1 pre-existing failure), and all source classes instantiate without abstract method errors. 55 minutes. | ||||||
| 101 | Vision-Agents | Runs | 96 / 100 | Go | 8,218 | |
Quickly build text, voice and video agents. Fast, Go based Agent backend with SDKs for every language. Sensible defaults for search, knowledge, skills... What the test found: The vision-agents core framework plus anthropic, gemini, openai, deepgram, elevenlabs, getstream, and smart_turn plugins are installed; 733 unit tests pass, the CLI binary responds, and all selected plugin imports resolve correctly. 42 minutes. | ||||||
| 102 | agent-governance-toolkit | Runs | 96 / 100 | Python | 6,594 | |
AI Agent Governance Toolkit, Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10... What the test found: All core Python packages install from source: agent-governance-toolkit-core, agent-governance-toolkit-cli, agent-control-specification (Rust wheel), agent-governance-toolkit-compliance. The agent-os test suite passes 2993/2993 selected tests, the ACS SDK test suite passes 306/306 selected tests, and the quickstart... 18 minutes. | ||||||
| 103 | intentkit | Runs | 96 / 100 | Python | 6,515 | |
IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you. What the test found: The IntentKit Python package installs with uv, 1854 tests pass (34 skipped on-chain tests need RPC endpoints), and the API server starts and serves OpenAPI docs on port 8000. 28 minutes. | ||||||
| 104 | agentscope-java | Runs | 96 / 100 | Java | 6,449 | |
Build distributed, production-grade, long-running agents. What the test found: AgentScope Java 2.0.4-SNAPSHOT builds and all 3082 test cases across core, harness, and extension modules pass with zero failures. 79 minutes. | ||||||
| 105 | 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. | ||||||
| 106 | LightAgent | Runs | 96 / 100 | Python | 1,248 | |
LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and... What the test found: LightAgent v0.10.2 installed in a Python 3.12 venv via pip install -e .; 287 unit tests pass covering memory, tools, tracing, guardrails, hooks, evaluation, review, flows, connectors, capabilities, skills, sessions, and runtime hardening; safe_expression and SharedMemoryPool verified working offline. 2 minutes. | ||||||
| 107 | agentic-awesome-skills | Runs | 95.7 / 100 | Python | 50,151 | |
3,000+ reusable AI agent skills for Claude Code, Codex, Cursor and Gemini CLI. AAS Core adds local catalog discovery, agent-owned selection and plan preview... What the test found: With Node 22.23.4 and PyYAML installed into /tmp, dependency install, the 2459-skill validation, the 241 web-app tests, the web-app build and the catalog build all succeed, the catalog app serves HTTP 200 for its main routes, the AAS CLI creates and validates a stack manifest and its MCP server answers initialize and... 21 minutes. | ||||||
| 108 | hive | Runs | 93.8 / 100 | Python | 11,167 | |
Multi-Agent Harness for Production AI What the test found: With the fixes, ./quickstart.sh completes and launches the Hive dashboard on an available local port; /api/health returned 200, Chromium rendered the Hive landing UI without page errors, and make test exited 0 with 2496 core and 4381 tools tests passed. 21 minutes. | ||||||
| 109 | kestra | Runs | 93.5 / 100 | Java | 30,314 | |
Orchestrate everything, everywhere. The open-source control plane for workflows across data, infrastructure, business processes and AI agents. Declarative... What the test found: Kestra v2.1.0-SNAPSHOT builds and tests successfully: backend core (3636/3646 pass, 2 environment-limited failures), executor (339/339), scheduler, worker (107/107), jdbc-h2 runner (98/98), and frontend (2743 unit tests + 282 storybook tests + type check + lint) all pass. 75 minutes. | ||||||
| 110 | 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. | ||||||
| 111 | 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. | ||||||
| 112 | Misaka-Agent | Runs | 93.3 / 100 | Python | 259 | |
A multi-agent research system for the humanities and social sciences. What the test found: MISAKA 0.18.11 installs and launches: --version prints 0.18.11, init creates a git project, the panel opens the setup wizard with fd and pdftotext present from the bundled archive, dm runs real turns that reply, and the test suite passes 4361 tests (the single remaining failure needs the optional ocrmypdf system... 22 minutes. | ||||||
| 113 | ralph-claude-code | Runs | 91 / 100 | Shell | 9,739 | |
Autonomous AI development loop for Claude Code with intelligent exit detection What the test found: Ralph is installed globally with 7 CLI commands, all 1319 tests pass, project setup works, and dry-run mode simulates loops without API calls. 13 minutes. | ||||||
| 114 | 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. | ||||||
| 115 | 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. | ||||||
| 116 | nanobrowser | Runs | 90.7 / 100 | TypeScript | 14,368 | |
Open-source AI agent for web automation. Use your real, logged-in browser to automate daily tasks. What the test found: Dependencies installed, project builds to dist/ (background.iife.js 1,848.81 kB, manifest.json), TypeScript type-check passes across all 15 packages, unit tests pass (14/14). 15 minutes. | ||||||
| 117 | autoclip | Runs | 90.7 / 100 | Python | 13,312 | |
AutoClip|一个链接,一键出片。开源 AI 视频剪辑桌面工具,将播客、访谈、课程等长视频自动剪成短视频,生成字幕、封面和发布文案,适配抖音、小红书、TikTok、Reels 与 YouTube Shorts。Open-source AI video clipping & content repurposing. What the test found: The AutoClip FastAPI backend serves all API health endpoints and the test suite passes with 103/103 tests passing. The frontend builds to production with Vite. 4 minutes. | ||||||
| 118 | PageIndex | Runs | 90 / 100 | Python | 40,743 | |
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG What the test found: PageIndex SDK v0.2.10 installed in a venv, all 796 unit tests pass, the CLI parses correctly, and the package imports without error. 3 minutes. | ||||||
| 119 | agency-agents-zh | Runs | 90 / 100 | Shell | 22,255 | |
🎭 277 个即插即用的 AI 专家角色, 支持 Claude Code/Cursor/Copilot 等 20 种工具,覆盖工程/设计/营销/金融等 20 个部门。含 64 个中国市场原创智能体(小红书/抖音/微信/飞书/钉钉/Qt 上位机/机械设计)。搭配编排器... What the test found: All 277 AI agent definition files are valid, the npm package builds, the conversion pipeline produces output for all 18 supported tools, and the install script copies agents to 6 detected tool directories without errors. 5 minutes. | ||||||
| 120 | ag-ui | Runs | 90 / 100 | TypeScript | 21,149 | |
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications. What the test found: All 35 Nx workspace projects build and 25/26 test suites pass (5531 tests), the dojo Next.js app serves HTTP 200 on localhost:3000. 14 minutes. | ||||||
| 121 | hermes-webui | Runs | 90 / 100 | Python | 19,609 | |
Hermes WebUI: The best way to use Hermes Agent from the web or from your phone! What the test found: Hermes WebUI boots from .venv, serves /health (HTTP 200), /api/onboarding/status returns full JSON, and 16893 of 17245 pytest tests pass. The missing Hermes agent (not installed) is the only missing component for full functionality. 38 minutes. | ||||||
| 122 | 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. | ||||||
| 123 | agent-scripts | Runs | 87.5 / 100 | Shell | 7,556 | |
Scripts for agents, shared between my repositories. What the test found: npm install completed, 30 npm node tests pass, 6 skill-cleaner tsx tests pass, 9 sync-skills bash tests pass, 5 clawsweeper-status tests pass, 4 npm-auth tests pass, 6 mac-release test suites pass (provider direct-refs 10/10), all 54 skill SKILL.md files validate, docs-list runs, video-transcript-downloader loads and... 10 minutes. | ||||||
| 124 | go-micro | Runs | 86 / 100 | Go | 23,077 | |
A framework for agents, tools and services What the test found: Go Micro builds and tests run with the CLI binary working; README updated to satisfy first-agent wayfinding doc integrity tests that enforce install-troubleshooting, micro agent demo/quickcheck/examples/zero-to-hero, examples/INDEX.md, first-agent, support, no-secret, your-first-agent, debugging-agents, inspect, and... 31 minutes. | ||||||
| 125 | ECC | Runs | 85 / 100 | JavaScript | 308,825 | |
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor... What the test found: npm install completed, all 10 CI validators pass, 4876 of 4906 tests pass; the only fix applied was guarding plan.adapter access in codex-user-config.js and ownership-guard.js to prevent TypeError when tests call applyInstallPlan without an adapter field. 42 minutes. | ||||||
| 126 | pydantic-ai | Runs | 84.8 / 100 | Python | 21,337 | |
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end. What the test found: The workspace installs and builds, the full CI-configured suite passed 15182 tests, and clai web served HTTP 200 on its health, configure, index, and chat endpoints using the built-in test model. 19 minutes. | ||||||
| 127 | zero2Agent | Runs | 80 / 100 | Python | 1,137 | |
面向大厂Agent研发岗位求职的agent教程网站,涵盖技术路线与面试八股文 What the test found: The examples/agent-api-lab Python test suite passes 18/18 tests and all CLI scenarios run correctly with the deterministic FakeProvider. The Jekyll static site cannot be built because Ruby is not available in this container. 1 minute. | ||||||
| 128 | lattice | Runs | 80 / 100 | Shell | 216 | |
Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just... What the test found: The Lattice skils install, distribution rebuild, and the portable verification runner all run correctly (27 skills installed, runner passes and fails as specified), while the website build remains blocked on the container's Node 18 versus the repo's pinned Node >=20 requirement. 15 minutes. | ||||||
| 129 | rocketride-server | Runs | 75 / 100 | Python | 19,992 | |
RocketRide is an open source AI meta-harness with the only enterprise-grade runtime built on C++. Build, test and publish durable agents that scale in... What the test found: The prebuilt RocketRide engine (v3.6.0.38) runs as a WebSocket server on port 5565, the Python client SDK (v1.6.0) installs and connects to it successfully, and the SDK's test suite executes real pipeline operations (launch/terminate/stream data/service discovery) against the engine. 22 minutes. | ||||||
| 130 | graphify | Runs | 66.7 / 100 | Python | 151,923 | |
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and... What the test found: graphifyy CLI installs, builds knowledge graphs from source code locally with tree-sitter AST, and passes 5234/5288 tests (11 pre-existing skillgen failures from shallow clone, no fix available). 11 minutes. | ||||||
| 131 | browser-use | Runs | 66.7 / 100 | Python | 121,752 | |
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API. What the test found: browser-use v0.13.10 installed in a Python 3.12 venv with uv, Chromium headless installed via playwright, and all 563 CI tests pass (529 passed, 34 skipped) after fixing 2 test identity comparison bugs in test_beta_agent.py that only manifest under xdist worker parallelism. 75 minutes. | ||||||
| 132 | OpenCLI | Runs | 66.7 / 100 | JavaScript | 31,225 | |
Make Any Website into CLI & Use your logged-in browser by AI agent. What the test found: OpenCLI 1.8.8 builds and runs on Node 22.14.0; 632 test files pass (7325 tests, 3 skipped) across unit, extension, adapter, smoke projects; CLI binary answers version 1.8.8 and lists 1366 registered commands. 27 minutes. | ||||||
| 133 | crewAI | Runs | 60 / 100 | Python | 61,170 | |
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly... What the test found: CrewAI v1.15.22 is installed with all optional extras, the CLI reports version 1.15.22, and 5424 of 5427 crewai tests pass (3 pre-existing unrelated failures), 87 crewai-core tests pass, 489 crewai-tools tests pass. 59 minutes. | ||||||
| 134 | text-to-cad | Runs | 60 / 100 | Python | 27,133 | |
Design physical products with AI What the test found: cadgen 0.6.6 installed from source: OCP kernel loads, CLI responds, Python test suites for cadgen CLI/store/memo and all eight tested skill packages pass, cross-language JS runtime bundle and Playwright snapshot browser present. 32 minutes. | ||||||
| 135 | adk-python | Runs | 60 / 100 | Python | 22,312 | |
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control. What the test found: uv virtual environment installed with all extras, google-adk 2.9.2 builds and imports, full unit test suite passes at 16167/16167 (0 failures, 83 skipped, 26 expected failures, 2 unexpected passes), CLICK-based CLI entry point is functional. 14 minutes. | ||||||
| 136 | edict | Runs | 60 / 100 | Python | 17,116 | |
🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System, 9 specialized AI agents with real-time dashboard, model config, and full audit trails What the test found: All 68 tests pass on Python 3.12.3; the dashboard HTTP server serves the React frontend, health check, and all API endpoints correctly. 6 minutes. | ||||||
| 137 | MiMo-Code | Runs | 60 / 100 | TypeScript | 13,799 | |
MiMo Code: Where Models and Agents Co-Evolve What the test found: MiMoCode CLI runs, typechecks, builds SDK, and passes ~2000+ tests across all core packages (agent, config, auth, git, tool, session, cli, server, workflow, effect, actor, history) with only ~15 environmentally-specific failures (umask, Bun version, test isolation). 37 minutes. | ||||||
| 138 | big-AGI | Runs | 60 / 100 | TypeScript | 7,167 | |
The AI workspace for experts. Switch across 800+ models mid-chat, tune 40+ parameters, Beam models side by side. BYO keys, self-hostable. Built on our... What the test found: All npm commands (install, test, build, tscheck, lint) pass cleanly on Node.js v22.14.0. The test suite runs 25 subtests: 4 pass (including a live OpenRouter model listing returning 388 models), 21 skip due to absent API keys, 0 fail. 9 minutes. | ||||||
| 139 | fast-agent | Runs | 60 / 100 | Python | 3,974 | |
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support What the test found: All 8730 unit tests pass, CLI boots and responds, playback LLM agent runs end-to-end, format/lint/typecheck all pass. 30 minutes. | ||||||
| 140 | Agentlas-OS | Runs | 60 / 100 | Python | 1,401 | |
The Open-Source AI Agent OS inspired by OpenAI Dots, Meta Muse, OpenClaw, Hermes & Mem0. Autonomous 3-tier headhunting, Receipt & Verifier loops, scoped... What the test found: Agentlas OS runtime v1.2.57 installed to ~/.agentlas/runtime/current with hephaestus doctor ok; ontology runtime operational with SQLite storage, Model2Vec int8 embeddings, FTS adapters, and auto-ingest working from ~/.agentlas/inbox directories. 6 minutes. | ||||||
| 141 | Deuz-SDK | Runs | 60 / 100 | TypeScript | 508 | |
TypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid... What the test found: Both @deuz-sdk/core and @deuz-sdk/react build from source and pass their full test suites (2635+39 tests passing) using MSW-mocked HTTP providers, requiring no real API credentials. 7 minutes. | ||||||
| 142 | agentsilex | Runs | 60 / 100 | Python | 460 | |
A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic. What the test found: All 30 tests pass, core Agent/Runner/Session/tool imports work, and the evaluation module loads successfully. 2 minutes. | ||||||
| 143 | agentdescent | Runs | 60 / 100 | - | 11 | |
Gradient descent, but the parameters are agents, a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the... What the test found: AgentDescent 0.5.0 is installed in a Python 3.12 venv; all 3026 tests pass; the demo and CLI (demo, init, plan, evolve, etc.) run offline with no API key needed. 48 minutes. | ||||||
| 144 | harness-sdk | Runs | 55 / 100 | TypeScript | 9,270 | |
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud. What the test found: Python SDK strands-agents v0.1.dev1 and strands-harness v0.0.1.dev1 installed from source, both packages import correctly, and over 2,000 unit tests pass across both packages. 68 minutes. | ||||||
| 145 | cognee | Runs | 50 / 100 | Python | 33,462 | |
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free What the test found: cognee 1.6.1 installs, builds, starts, and runs: the local LLM-free remember/recall pipeline produces search results from ingested text, the CLI demo loads a bundled knowledge graph, the FastAPI server answers HTTP 200 on /health, and 388 unit tests pass across 5 test suites with zero failures. 33 minutes. | ||||||
| 146 | txtai | Runs | 47.4 / 100 | Python | 13,713 | |
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows What the test found: txtai 9.14.0 installed in venv, all core embeddings/graph/workflow/agent/cloud/vector/scoring tests pass, API responds to search/index/count endpoints with real model inference, ~470 automated tests pass across 30 test suites. 83 minutes. | ||||||
| 147 | crawl4ai | Runs | 45.7 / 100 | Python | 87,664 | |
Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this... What the test found: Crawl4AI 0.9.4 installed in venv, Playwright chromium browser downloaded, DB initialized, AsyncWebCrawler can crawl real URLs with markdown output, cache operations work, and 360 core tests pass with 11 skipped. 14 minutes. | ||||||
| 148 | Upsonic | Runs | 33.3 / 100 | Python | 7,968 | |
Build autonomous AI agents in Python. What the test found: Upsonic v0.77.3 installed from source in editable mode; all 1490+ tests pass; CLI is functional. 23 minutes. | ||||||
| 149 | 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. | ||||||
| 150 | mem0 | Runs with mocks | 92 / 100 | Python | 69,343 | |
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production. What the test found: mem0ai 2.2.0 installed and tested: 1210 tests passing across the core SDK, LLM providers, embeddings, client, telemetry, proxy, configs, and Qdrant vector store, with one bugfix in proxy/main.py to guard against UnboundLocalError on memories_text. 23 minutes. | ||||||
| 151 | marketingskills | Runs with mocks | 92 / 100 | JavaScript | 62,012 | |
Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering. What the test found: All 50 skills validated against the Agent Skills spec (both internal and official skills-ref validators), all 26 CLI contract-test suites pass with mocked HTTP, all 65 CLI tools parse cleanly, all 3 JSON manifests are well-formed, and skillkit can enumerate 53 available skills from the repo. 5 minutes. | ||||||
| 152 | DeepTutor | Runs with mocks | 92 / 100 | Python | 61,564 | |
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/. What the test found: Package installed via pip install -e .[dev] with partners extra. LLM features require OpenAI/etc credentials (deeptutor doctor reports No active LLM model). Test suite passes across core, API, CLI, services, book, reading, video learning, agents, capabilities, tools, knowledge, runtime, and plugins modules after 4... 81 minutes. | ||||||
| 153 | nanobot | Runs with mocks | 92 / 100 | Python | 50,269 | |
Your lightweight open-source personal agent. What the test found: After pinning mcp<1.30 and relaxing two width-sensitive CLI assertions, Python installs editable, the 6785-test suite, 1125 WebUI tests and basedpyright all pass, and against a local mock provider the CLI agent, OpenAI-compatible API server (JSON and SSE), gateway WebSocket chat and native TUI all returned 'Hello from... 29 minutes. | ||||||
| 154 | Claude-Code-Game-Studios | Runs with mocks | 92 / 100 | Shell | 40,598 | |
Turn Claude Code into a full game dev studio, 49 AI agents, 75 workflow skills, and a complete coordination system mirroring real studio hierarchy. What the test found: The Claude Code Game Studios framework repository is fully verified: all 14 hooks run cleanly (session-start reports review mode solo and detects fresh project, detect-gaps identifies new project and suggests /start, validate-* hooks exit 0 on non-matching context, yaml-helper resolves config correctly), all 8 scripts... 4 minutes. | ||||||
| 155 | Jobs_Applier_AI_Agent_AIHawk | Runs with mocks | 92 / 100 | Python | 32,611 | |
AIHawk: AI job application bot, automated job search, job hunting, auto-apply to resume-matching jobs while you sleep. What the test found: The repository installs from source with all dependencies, the full automated suite passes (266 non-browser + 6 real-browser), and an end-to-end search-and-apply run through a mock OrcaRouter over a real local job index fills and submits a live Greenhouse application form, writing a decoded proof screenshot. 51 minutes. | ||||||
| 156 | artemis | Runs with mocks | 92 / 100 | Python | 17,895 | |
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with... What the test found: uv sync --dev succeeded; pytest exits 0 with 2185 passed, 10 skipped, 8 deselected; 'artemis ui' served the web console with HTTP 200 on /, /admin, /docs, and /health; --version answered v1.0; doctor and status CLI commands run, and the ADB daemon started from the bundled binary. 61 minutes. | ||||||
| 157 | E2B | Runs with mocks | 92 / 100 | Python | 14,967 | |
Open-source, secure environment with real-world tools for enterprise-grade agents. What the test found: The repository installs and builds with the pinned toolchain, the CLI launches at version 2.20.0, the no-credential CLI and Python offline suites pass, and an isolated installed CLI completed a mocked template build including a COPY upload. 10 minutes. | ||||||
| 158 | Agent-S | Runs with mocks | 92 / 100 | Python | 13,019 | |
Agent S: the state-of-the-art open source computer use agents What the test found: gui-agents v0.3.2 installed and its 5 unit tests pass; all S1/S2/S2.5/S3 modules import and engine constructors work correctly. 8 minutes. | ||||||
| 159 | MemOS | Runs with mocks | 92 / 100 | TypeScript | 12,479 | |
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek... What the test found: Python 3.12.3 venv with Poetry, MemoryOS 2.0.33 installed, library imports, CLI runs, all 875 tests pass with 9 skipped for expected missing infrastructure (Neo4j, Redis). 14 minutes. | ||||||
| 160 | aichat | Runs with mocks | 92 / 100 | Rust | 10,593 | |
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more. What the test found: aichat 0.30.0 builds from source, passes all 21 unit tests, and successfully proxies requests to an OpenAI-compatible API backend including chat completions (200), model listing, and web playground (200). 7 minutes. | ||||||
| 161 | CyberStrikeAI | Runs with mocks | 92 / 100 | Go | 8,927 | |
The system of action for AI-native cybersecurity, where intent becomes governed execution, evidence becomes operational memory, and every operation improves... What the test found: The CyberStrikeAI binary builds cleanly with Go 1.25.0, serves its web UI on HTTP port 8080 with a 200 status, accepts admin login via POST /api/auth/login returning a full permissions token, and all 28 internal Go test packages (including database, handler, multiagent, security, mcp, and workflow) pass without... 17 minutes. | ||||||
| 162 | awesome-agentic-ai-zh | Runs with mocks | 92 / 100 | Python | 8,853 | |
A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文... What the test found: Mkdocs documentation site builds successfully (106M), all 1083 script-level tests pass, and all 51 offline example tests pass with mocked dependencies; the project is a learning roadmap with runnable exercises for LLM agent development across OpenAI, Anthropic, and Ollama-compatible providers. 7 minutes. | ||||||
| 163 | MiroThinker | Runs with mocks | 92 / 100 | Python | 8,454 | |
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the... What the test found: uv sync installs cleanly, the agent pipeline executes a real MCP tool through a local mock LLM and completes with status success and boxed answer 'answer-is-42', 39 lobehub parser tests pass, and the trace dashboard serves HTTP 200. 38 minutes. | ||||||
| 164 | open-multi-agent | Runs with mocks | 92 / 100 | TypeScript | 7,070 | |
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it. What the test found: The monorepo installs, builds, passes 2350 unit tests across all 4 workspaces plus the benchmark harness, and the CLI prints help, all with Node.js 22, no API keys or network required. 4 minutes. | ||||||
| 165 | MiroFlow | Runs with mocks | 92 / 100 | Python | 3,158 | |
🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI What the test found: The project installs with uv sync, and the trace pipeline executes end-to-end: it reads XLSX files via markitdown-mcp, calls a mock OpenRouter API, and produces the expected boxed answer. The onnxruntime dependency logs non-blocking CPU-affinity warnings in this container. 33 minutes. | ||||||
| 166 | agent-landing-zone | Runs with mocks | 92 / 100 | Python | 1,202 | |
Enterprise-grade landing zone for AI agent applications on Azure. Deploy the secure infrastructure, the agent app, or both, built on Microsoft Foundry and... What the test found: GPT-RAG Python configuration modules install cleanly and all 280 tests pass on the test suite, covering deployment composition, topology resolution, hosted access, private network validation, release contracts, and utility modules. 3 minutes. | ||||||
| 167 | GPT-RAG | Runs with mocks | 92 / 100 | Python | 1,202 | |
Enterprise-grade landing zone for AI agent applications on Azure. Deploy the secure infrastructure, the agent app, or both, built on Microsoft Foundry and... What the test found: Python virtual environment installed, all config and utility modules import cleanly, and full unit test suite passes (469/469) with no Azure credentials or cloud services required. 3 minutes. | ||||||
| 168 | 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. | ||||||
| 169 | CyberClaw | Runs with mocks | 92 / 100 | Python | 346 | |
👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态 What the test found: Installed and the 130 tests all pass. The CLI starts, connects to an LLM provider, completes a tool-augmented conversation (user query -> get_current_time tool call -> mock response displayed), and exits cleanly. 4 minutes. | ||||||
| 170 | vizra-adk | Runs with mocks | 92 / 100 | PHP | 295 | |
Build, test, and deploy intelligent AI agents the Laravel way What the test found: PHP 8.4.26 and Composer 2.10.3 installed via static binaries, all 136 Composer dependencies resolved and autoloaded, and the Pest test suite passes fully (1084/1084 passing tests) using SQLite in-memory database and mock LLM providers. 9 minutes. | ||||||
| 171 | streamcore-server | Runs with mocks | 92 / 100 | Go | 248 | |
Open-source realtime voice agent server in Go with WebRTC (WHIP), barge-in, streaming STT/LLM/TTS pipelines, plugin system, multi-language SDKs, SIP telephony... What the test found: The Go server builds, lints with no formatting issues, passes all 15 test suites, and starts on :8080 responding to /health and /whip endpoints. 5 minutes. | ||||||
| 172 | Sico | Runs with mocks | 89.1 / 100 | Python | 284 | |
An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets. What the test found: Core Python service tests pass (1564/1564), Go backend builds and passes 44 test packages, frontend SPA builds and app tests pass (161/161). 44 minutes. | ||||||
| 173 | sre | Runs with mocks | 86.3 / 100 | TypeScript | 1,305 | |
The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build... What the test found: SmythOS SRE v0.5.0 monorepo installs with pnpm; CLI reports version 0.4.0 and responds to commands; core unit test suite passes 368/377 tests (19 failures require real AWS/OpenAI API credentials which cannot be mocked); SRE runtime initializes with Storage (LocalStorage) and Cache (RAM) connectors operational... 27 minutes. | ||||||
| 174 | parlant | Runs with mocks | 86.2 / 100 | Python | 18,339 | |
Parlant lets you build and operate reliable CX and support agents from your own AI coding agents. What the test found: With a schema-correct mock NLP backend, the Parlant server started on port 18999, answered /healthz 200, created agents/guidelines/sessions (201), and ran the engine to completion status; 208 API tests passed while the parlant CLI remained unimportable. 54 minutes. | ||||||
| 175 | learn-harness-engineering | Runs with mocks | 86 / 100 | TypeScript | 25,854 | |
Harness engineering beginner tutorial, from 0 to 1 What the test found: Root npm install succeeded, VitePress docs dev server serves all pages with 200, all 15 project Electron apps build successfully, and project-01 starter Electron app launches and stays running in the container. 15 minutes. | ||||||
| 176 | blades | Runs with mocks | 86 / 100 | Go | 825 | |
Blades is a Go-based multimodal AI Agent framework. What the test found: Go installed user-space, all modules build, all 29 test packages pass, and the blades CLI init/doctor/run commands work with blades run answering correctly against a local OpenAI-compatible mock. 17 minutes. | ||||||
| 177 | agno | Runs with mocks | 85.3 / 100 | Python | 43,260 | |
The self-managing agent platform What the test found: Agno SDK v3.0.11 installed and imported; CLI functional; core agent/context/reasoning/utils/model/tool test suites (5000+ tests) pass; format script passes; validate passes ruff checks but has 60 pre-existing mypy errors in the agno library. 62 minutes. | ||||||
| 178 | Director | Runs with mocks | 85.3 / 100 | Python | 1,591 | |
AI video agents framework for next-gen video interactions and workflows. What the test found: Backend Flask server starts on port 8000 with SQLite database responding to /agent/, /session/, and /config/check endpoints. Frontend Vite dev server starts on port 8080 and production build completes. The project requires a real VideoDB API key for video-related endpoints and real LLM API keys for agent functionality. 4 minutes. | ||||||
| 179 | Octopus-SI-OS | Runs with mocks | 85.3 / 100 | Rust | 822 | |
A self-evolving agentic OS. A new architecture for agent execution, built on operating-system principles, with the harness as a path toward superintelligence. What the test found: The Rust kernel workspace (18 core crates) builds and tests pass at 6053/6124 on Linux x86_64. The octopus CLI binary compiles and runs doctor/help. The audio_device_session crate is excluded (ALSA headers unavailable without root). One schema file was regenerated to match its Rust type. All 71 test failures stem from... 36 minutes. | ||||||
| 180 | nuwa-skill | Runs with mocks | 84.7 / 100 | Python | 38,807 | |
你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式, 心智模型、决策启发式、表达DNA。Distill how anyone thinks. What the test found: nuwa-skill installed to ~/.codex/skills/nuwa-skill/SKILL.md with proper frontmatter (name: huashu-nuwa). All 7 Python scripts execute without errors. 15 example skills present with SKILL.md, FIDELITY.md (Grade A, 89-97/100), and references/. Dependencies yt-dlp (2026.08.19) and Pillow (12.3.0) installed and... 14 minutes. | ||||||
| 181 | AWorld | Runs with mocks | 84.5 / 100 | Python | 1,249 | |
Search, understand, reproduce, and improve an idea with ease What the test found: AWorld and AWorld-CLI packages install and build successfully. All 170 ACP unit tests pass with memory bootstrap gracefully degrading when no LLM API key is configured. The ACP self-test bridge validates 15 phase-1 protocol cases end-to-end. The aworld and aworld-cli entry points respond to --help correctly. 51 minutes. | ||||||
| 182 | 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. | ||||||
| 183 | lamda | Runs with mocks | 56 / 100 | Python | 8,761 | |
Android Full-Stack Device Control Platform: WebRTC/H.264 remote desktop, UI/OCR/image-matching automation, one-click MITM, built-in Frida, proxy/VPN/frp/P2P... What the test found: lamda Python client v10.8 installs, all modules import, and the gRPC protocol stack works end-to-end via a mocked server. 7 minutes. | ||||||
| 184 | full-stack-ai-agent-template | Runs with mocks | 56 / 100 | Python | 2,005 | |
Full-stack AI app generator, FastAPI + Next.js with AI Agents, RAG, streaming, auth, and 20+ integrations out of the box. What the test found: All 681 tests pass; the CLI generates projects and runs type-checking on all generated matrix configurations including pydantic_deep_pg, pydantic_ai_code_execution, and pydantic_ai_skills without errors. 37 minutes. | ||||||
| 185 | agents-universe | Runs with mocks | 56 / 100 | Python | 972 | |
不是问答机器人,而是能真正干活的数字分身。共享智能体,共享项目上下文,让项目所有成员一起协同工作。同时智能体会像人一样通过资料或者工作抽象和总结经验到项目上下文中 What the test found: Backend API runs on port 8002 (SQLite, auth-bypass) with /health 200, project+knowledge APIs working, and a real agent turn streamed an SSE-mocked response end-to-end; 7 agent-core sandbox/shell tests remain red in this container due to missing root for python symlink/user-site and venv path layout. 37 minutes. | ||||||
| 186 | alphora | Runs with mocks | 52.7 / 100 | Python | 348 | |
A Production-Ready Framework for Building Composable AI Agents What the test found: Alphora 1.3.4 is installed in a venv, all 22 tutorials run without errors, the alphora-web frontend server responds to HTTP 200 on /v1/health, and the publish_agent_api server accepts streaming and non-streaming chat completion requests against a mock OpenAI backend. 17 minutes. | ||||||
| 187 | vibe-kanban | Runs with mocks | 46 / 100 | Rust | 28,784 | |
Get 10X more out of Claude Code, Codex or any coding agent What the test found: Rust workspace (excluding tauri-app) compiles and passes cargo check. Server binary builds and starts, binding to random available port and responding to HTTP requests. 3 crate test suites pass (10/10 unit tests). Frontend TypeScript type checks pass for web-core and local-web. The npx CLI, Tauri desktop app, and web... 82 minutes. | ||||||
| 188 | openclacky | Could not verify | 40 / 100 | Ruby | 1,209 | |
The Most Token-Efficient Lightweight AI Agent What the test found: could not be verified; the log shows where it stopped. 87 minutes. | ||||||
| 189 | OpenBot | Could not verify | 38.6 / 100 | TypeScript | 13,196 | |
The open, self-hostable alternative to closed AI bots. Production-ready, fully customizable, and plugs into every stack: any agent, any model, any tool. What the test found: bun install and all 3985 non-integration unit tests pass. The 69 failures are all infrastructure-gated (no PostgreSQL for integration tests, no Docker for compose tests, 2 pre-existing Mastra .env leakage failures). 49 minutes. | ||||||
| 190 | 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. | ||||||
| 191 | astrid | Could not verify | 20 / 100 | Rust | 10,290 | |
Astrid is a portable, capability-secure operating system for composable software. What the test found: could not be verified; the log shows where it stopped. 72 minutes. | ||||||
| 192 | AgenticX | Could not verify | 20 / 100 | Python | 1,159 | |
AgenticX is a unified, production-ready multi-agent platform, Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration... What the test found: could not be verified; the log shows where it stopped. | ||||||
| 193 | skillhub | Could not verify | 10 / 100 | Java | 5,465 | |
Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with... What the test found: All 4 backend Maven modules compile and 1483 of 1489 tests pass (6 fail only due to Docker unavailability). Frontend dependencies install and individual vitest tests pass. The full app cannot start because Docker is not available to launch Postgres, Redis, and MinIO. 88 minutes. | ||||||
| - | QwenPaw | Not yet tested | - | Python | 38,104 | - |
| - | dapr | Not yet tested | - | Go | 26,213 | - |
| - | moli | Not yet tested | - | Rust | 24,245 | - |
| - | munder-difflin | Not yet tested | - | TypeScript | 9,693 | - |
| - | forall | Not yet tested | - | Rust | 578 | - |
| - | agentica | Not yet tested | - | Python | 367 | - |
| - | mofa | Not yet tested | - | Rust | 300 | - |
| - | designpowers | Not yet tested | - | Shell | 263 | - |
| - | dat | Not yet tested | - | Java | 258 | - |
| - | LeAgent | Not yet tested | - | Python | 246 | - |
| - | agents-aea | Not yet tested | - | Python | 241 | - |
| - | jarviscore-framework | Not yet tested | - | Python | 126 | - |
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: 148 projects ran as-is, 39 with mocks, 6 could not be verified, 12 still waiting. Languages tested: C++, Elixir, Go, Java, JavaScript, Makefile, PHP, Python, Ruby, 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?
12 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
- open source coding agents (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 Agentlas-OS, OpenCLI, PraisonAI, QuantDinger, Yuxi, agents-universe, autoclip, browser-use, commonly, harnessrouter, mnemon, moli, nanobrowser, open-multi-agent, plandex, rocketride-server, steel-browser, swarmclaw with this list)
- MCP servers (shares Deuz-SDK, Douyin_TikTok_Download_API, Graft, QuantDinger, Trail-Code, commonly, fast-agent, gentle-ai, lamda, rea, rocketride-server, trpc-agent-go, xerj with this list)
- browser automation tools (shares Jobs_Applier_AI_Agent, Jobs_Applier_AI_Agent_AIHawk, OpenBot, OpenCLI, browser-use, invisible_dots, moli, nanobrowser, page-agent, steel-browser with this list)
- developer CLI tools (shares DeepSeek-Reasonix, Graft, Trail-Code, herdr, pixel-agents, plandex, rea with this list)
- web scraping tools (shares Douyin_TikTok_Download_API, ai-website-cloner-template, browser-use, crawl4ai, moli, nanobrowser with this list)
- vector databases (shares PageIndex, anything-llm, cognee, txtai, xerj with this list)
- workflow automation tools (shares Vibe-Skills, edict, hive, invisible_dots, nanobot with this list)
- observability tools (shares open-multi-agent, trpc-agent-go, voltagent with this list)
- project management tools (shares ccpm, edict, vibe-kanban with this list)
- LLM gateways (shares 9router, EnterpriseAgentFramework with this list)
- Open source databases, installed and queried (shares dolt, xerj with this list)
- low-code platforms (shares agency-agents-zh, kestra with this list)
- search engines (shares txtai, xerj with this list)
- speech tools (shares Douyin_TikTok_Download_API, lemo-opuscar with this list)
- open source video editors (shares autoclip with this list)
- wikis (shares book-to-skill with this list)
- API clients
- API gateways
- CI/CD tools
- CMS platforms
- VPN tools
- backup tools
- code editors
- e-commerce platforms
- ebook readers
- game engines
- open source games
- home automation tools
- map tools
- message queues
- Open source music servers, installed and played
- Open source office suites, installed and launched
- self-hosted password managers
- screen recorders
- self-hosted analytics
- static site generators
- uptime monitors
- video players
- whiteboard tools
- self-hosted Notion alternatives
- self-hosted dashboards
- self-hosted git servers