Open source LLM gateways, installed and run
LLM and AI gateways 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.
43 of 51 tested projects run. 6 more waiting for a test.
In short: 32 of the 51 tested projects started as-is on a fresh machine: 9router, coai, gpt-load, plano, CPA-Manager-Plus, OrcaRouter-Lite, krakend-ce, and CliRelay, and 24 more. 11 more started once a stand-in replaced a service they expect, such as a database: ccs, future-agi, GoModel, copilot-api, respan-gateway, Lynkr, sagify, and grok2api-egress-enhancements, and 3 more. 8 could not be verified: digiRunner-Open-Source, higress, router, dario, bitrouter, orbit, agentgateway, and agent-router; 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 | 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. | ||||||
| 2 | coai | Runs | 100 / 100 | TypeScript | 9,343 | |
🚀 Next Gen Multi-tenant AI One-Stop Solution. Builtin Admin & Billing System. Enterprise-Grade Unified LLM Gateway Support for 200+ Models And 35+ Providers... What the test found: CoAI.Dev builds and runs on port 8094 using SQLite (no MySQL) and a fake Redis mock, with login, user info, admin analytics, quota, subscription, channel management, and model listing endpoints all responding correctly. 18 minutes. | ||||||
| 3 | gpt-load | Runs | 100 / 100 | Go | 7,245 | |
Self-hosted AI gateway for multi-channel, multi-credential setups, API keys and subscription accounts, scheduling, failover, request logs and usage. 自托管 AI... What the test found: GPT-Load 2.0 binary builds, web UI compiles, server starts on 127.0.0.1:3001, health endpoint returns HTTP 200, auto-generates AUTH_KEY, and shuts down gracefully with all database migrations completed and catalog synced. 8 minutes. | ||||||
| 4 | plano | Runs | 100 / 100 | Rust | 7,118 | |
Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused... What the test found: Plano CLI 0.4.36 is installed, 110 CLI tests pass, planoai up runs the native Envoy+brightstaff stack (healthz 200), end-to-end chat completions through localhost:12000 return the mock upstream's JSON, and planoai down cleanly stops the services. 36 minutes. | ||||||
| 5 | CPA-Manager-Plus | Runs | 100 / 100 | Go | 4,100 | |
A self-hosted CPA / CLIProxyAPI management panel and AI gateway observability dashboard for requests, usage, cost, quota, failures, and account health. What the test found: CPA Manager Plus web app builds to a single-file index.html, Go manager server compiles and listens on :18317 with /health returning 200, all 4156 frontend and all Go backend tests pass without errors. 24 minutes. | ||||||
| 6 | OrcaRouter-Lite | Runs | 100 / 100 | Python | 3,057 | |
Self-hosted LLM router with a managed safety net. OpenAI-compatible. BYOK. Single-workspace. Streaming. For more advanced routing choose hosted OrcaRouter What the test found: OrcaRouter Lite installs from source in a venv, all 703 tests pass, the server starts and responds to /health (200) and /v1/models (200 with 666 models) with valid auth. 3 minutes. | ||||||
| 7 | krakend-ce | Runs | 100 / 100 | Go | 2,703 | |
KrakenD Community Edition: High-performance, stateless, declarative, API Gateway written in Go. What the test found: KrakenD-CE v2.13.11 binary built from source, all 57 integration tests pass, and the gateway starts and listens on port 8080. 4 minutes. | ||||||
| 8 | CliRelay | Runs | 100 / 100 | Go | 1,064 | |
Self-hosted AI gateway for coding CLIs, one OpenAI/Claude/Gemini/Codex-compatible endpoint, with a multi-tenant web console, request logs, and spend quotas. What the test found: Project builds and all 4586 unit tests pass; server requires PostgreSQL and Redis at runtime, which cannot be installed without root in this container. 11 minutes. | ||||||
| 9 | 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. | ||||||
| 10 | gemini-web2api-go | Runs | 100 / 100 | Go | 991 | |
Gemini web → OpenAI-compatible + native Gemini API, self-hosted, no API key. Gemini 4 Argon from a paid account cookie, strict_model (429 instead of a silent... What the test found: Binary builds and runs, serves OpenAI-compatible API at :8083, handles non-streaming and streaming chat completions, /v1/responses, /v1/models, and admin UI with SQLite persistence, all verified with real Gemini responses. 5 minutes. | ||||||
| 11 | 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. | ||||||
| 12 | AstrLink | Runs | 100 / 100 | Go | 603 | |
A local AI gateway for AI agents, unifying your subscriptions and API providers with smart routing and on-device privacy protection. What the test found: AstrLink core gateway builds, launches with control-token-stdin, authenticates via control API, creates access tokens, and responds to inference requests with correct routing errors. All 37 Go packages pass tests (normal + race), 1739 frontend tests pass, and both Rust workers compile cleanly. 18 minutes. | ||||||
| 13 | RabiRoute | Runs | 100 / 100 | TypeScript | 493 | |
Self-hosted gateway that bridges QQ, WeChat/WeCom and Feishu chat to your existing Codex or agent task, remote control from your phone, schedules and role... What the test found: A clean-state Linux Host stayed healthy with Manager HTTP 200, businessReady=true, two seeded roles, one ready route, 29 catalog plugins, 33/33 advertised assets returning 200, and a successfully opened NapCat WebSocket, while optional speech capture and NapCat HTTP profile access remained unavailable. 45 minutes. | ||||||
| 14 | oh-my-cpa | Runs | 100 / 100 | TypeScript | 479 | |
Modern web console for CLIProxyAPI v8+ with provider and OAuth management, live routing, request analytics, pricing, and MCP. What the test found: The binary builds, all Go packages test pass, the full frontend builds and embeds, the app serves the SPA and health endpoint with status ok in both demo mode (in-process fixture) and non-demo mode (with a mock CPA answering the v8 API probe). 16 minutes. | ||||||
| 15 | kiji-proxy | Runs | 100 / 100 | Go | 456 | |
Privacy proxy for your OpenAI requests What the test found: Installed and verified: Go backend builds and serves /health 200 with the quantized ONNX PII model loaded, masks real emails end-to-end via /api/pii/check, Unix desktop Electron app launches and stays running on the virtual display, Python (2 passed) and Go (512 passed) unit suites are green, and the frontend... 27 minutes. | ||||||
| 16 | ccLoad | Runs | 100 / 100 | Go | 445 | |
Self-hosted AI API gateway for Claude Code, Codex and Gemini: pool API keys and subscription accounts behind one endpoint with failover, protocol conversion... What the test found: Binary builds, server starts and listens on :8080, health endpoint returns 200, admin login/auth flow works, all 49 Go test packages pass, all 284 JS frontend tests pass, model catalog syncs 244 models from models.dev. 10 minutes. | ||||||
| 17 | antirion | Runs | 100 / 100 | Rust | 429 | |
🕷️ The fastest open-source AI Gateway and LLM Gateway, one binary with built-in console to route, secure, budget and observe every LLM call across OpenAI... What the test found: The Antirion AI gateway builds from source, its test suite passes 1044/1044 tests, the binary starts in standalone mode with the embedded store, and successfully routes a chat completion request through a provider, deployment, model, and key to a mock upstream and back with HTTP 200. 16 minutes. | ||||||
| 18 | privacy-filter | Runs | 100 / 100 | Go | 341 | |
LLM privacy gateway in Go, millisecond-latency PII and secret redaction. Used in production by PackyCode. What the test found: Both binaries build, all 3153+28 tests pass, HTTP server serves /health /redact /redact/batch correctly with 221 gitleaks rules loaded, gRPC server starts on :8089, and benchmarks show sub-ms latency on 2KB text. 3 minutes. | ||||||
| 19 | llmio | Runs | 100 / 100 | Go | 322 | |
Unified LLM gateway with weighted load balancing, observability & cost tracking. 统一的 LLM 网关,提供权重负载均衡、可观测性与费用追踪。 What the test found: The LLMIO Go server builds, the webui builds via pnpm, all 31 Go unit tests pass, and the server starts on :7070 serving the webui and responding to all API endpoints. 16 minutes. | ||||||
| 20 | ai-gateway | Runs | 100 / 100 | Go | 299 | |
Unified AI Gateway for 30+ LLMs (OpenAI, Anthropic, Bedrock, Azure etc) with Caching, Guardrails, A/B test & cost controls. Go-native Fastest & Scalable AI... What the test found: Go 1.25.14 installed from tarball, ferrogw binary built at 42 MB binary, server starts and responds 200 on /livez, /readyz, and /health, 'go test' over all 89 packages passes with zero failures, 'ferrogw validate' confirms config valid. 10 minutes. | ||||||
| 21 | gptGrok2api | Runs | 100 / 100 | Python | 293 | |
ChatGPT/GPT 注册机|Grok 注册机|全自动纯协议注册,支持 OAuth、邮箱接码、账号池、代理轮换及 OpenAI/Anthropic 兼容 API。GPT/Grok Account Creator & API Gateway with automated registration, email... What the test found: Backend server starts cleanly, responds to authenticated requests on /v1/models with a full model list, auth enforcement works correctly, and all 623 Python tests pass. 14 minutes. | ||||||
| 22 | busbar | Runs | 100 / 100 | Rust | 237 | |
The execution control plane for AI agents. Govern every model request, MCP tool call, A2A delegation, and downstream action, while keeping your native... What the test found: Busbar 1.5.5 builds, passes its full test suite (3085 unit tests), validates a minimal config, and serves /healthz (200), /stats (valid JSON), /v1/models (model list), admin /auth, and admin /models endpoints on both the data (:8090) and admin (:8091) listeners. 14 minutes. | ||||||
| 23 | Serein | Runs | 97.5 / 100 | Python | 256 | |
雨落下的地方,记忆会再次开花。可自部署的 AI 长期记忆与聊天网关。Self-hosted AI memory & chat gateway for long-term conversations. What the test found: Serein installs and builds in a clean venv, the Python suite runs 2178 passed with the web suite 130 passed, and the local memory and gateway services answer /ready and /health with 200 while unauthenticated root returns 401. 87 minutes. | ||||||
| 24 | casdoor | Runs | 96 / 100 | Go | 14,924 | |
An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC... What the test found: Casdoor server runs on port 8000 with SQLite, frontend serves index.html (200), login authenticates admin/123 via JSON API, OpenID Connect configuration endpoint returns valid metadata, and the API returns organization and user data from the demo seed. 14 minutes. | ||||||
| 25 | 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. | ||||||
| 26 | 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. | ||||||
| 27 | otari | Runs | 96 / 100 | Python | 960 | |
Open-source AI gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking. What the test found: The Otari LLM gateway installed from source with uv, boots as a standalone server on port 8000 serving the management API, bootstrap, health, docs, OpenAPI spec, and tutorial root page, and the OSS edition smoke test exercises all key lifecycle stages (health, bootstrap, user/keys, providers, routing, completions... 20 minutes. | ||||||
| 28 | ThinkWatch-Lite | Runs | 92.7 / 100 | TypeScript | 946 | |
Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays... What the test found: Frontend builds successfully (vite), vitest suite passes 611/611 tests, Rust crate tw-adopt passes 67/67 tests, Rust crate tw-scan passes 35/35 tests; the main Tauri desktop binary is blocked by missing glib2/gtk3/webkit2gtk development packages that cannot be installed without root. 8 minutes. | ||||||
| 29 | gateway | Runs | 60 / 100 | TypeScript | 13,429 | |
A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API. What the test found: npm install and build succeed, the Node.js server starts on port 8787 and responds 200 on /v1, 170 unit tests pass. 30 minutes. | ||||||
| 30 | litellm-agent-control-plane | Runs | 60 / 100 | Rust | 1,336 | |
1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents. What the test found: The LiteLLM Agent Control Plane Rust binary compiles from source, its full test suite passes (211 passed, 0 failed, 7 ignored for missing live credentials), the server starts on port 4000, /health returns 200, and /v1/models returns configured models. 8 minutes. | ||||||
| 31 | TokenHub | Runs | 50 / 100 | Go | 1,449 | |
TokenHub gives enterprises a private gateway to unify AI model access and governance, making every request controllable, traceable, and attributable. What the test found: TokenHub Go backend built and launched on :8080 with SQLite, serving health/liveness/readiness at HTTP 200 and an OpenAPI spec with 21 endpoints. Frontend builds and all 521 tests pass. Backend non-server test suite passes. 178 repo gate tests pass. 37 minutes. | ||||||
| 32 | temps | Runs | 50 / 100 | Rust | 941 | |
AI-native open-source alternative to Vercel + Sentry + PostHog + Pingdom + Resend + E2B. 440+ CLI operations with drop-in skills for Claude Code, Codex &... What the test found: Temps built from source runs a control-plane server on 127.0.0.1:8081 against a Postgres 17.4 + TimescaleDB/pgvector/pg_tsparser mock database, serves /health 200 and an authenticated API that created and listed a real project; all 276 database migrations and the web console build complete successfully. 85 minutes. | ||||||
| 33 | ccs | Runs with mocks | 92 / 100 | TypeScript | 2,907 | |
Switch between Claude accounts, Gemini, Copilot, OpenRouter (300+ models) via CLIProxyAPI OAuth proxy. Visual dashboard, remote proxy support, WebSearch... What the test found: CCS v8.10.0 builds and runs. The CLI help and version commands respond. 29/29 cursor daemon tests pass after the port validation fix. 125/127 fast-bucket test files pass; the 2 that fail (1 https-tunnel, 4 websearch in shared bucket only, 3 tool-sanitization) are pre-existing and not caused by the change. 20 minutes. | ||||||
| 34 | future-agi | Runs with mocks | 92 / 100 | Python | 2,286 | |
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway ·... What the test found: Frontend dependencies installed with yarn, unit and integration tests pass (11/11) using jsdom environment. Backend dependencies installed via uv sync (441 packages). Django 5.1.8 and Django REST framework import correctly. Backend cannot fully start or run tests without Docker for PostgreSQL, ClickHouse, Redis, and... 50 minutes. | ||||||
| 35 | GoModel | Runs with mocks | 92 / 100 | Go | 1,322 | |
AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI... What the test found: The GoModel binary builds and runs, serving health (200 OK), dashboard (200 OK), and models endpoint (200 OK); all 101 test packages (internal, e2e, contract) pass with zero failures. 10 minutes. | ||||||
| 36 | copilot-api | Runs with mocks | 92 / 100 | TypeScript | 1,129 | |
GitHub Copilot, OpenAI Codex, OpenCode Go, and third-party AI provider gateway with OpenAI and Anthropic API compatibility. What the test found: copilot-api built, 949/950 tests pass, and the gateway serves /v1/models on port 14142 with a configured mock provider. 5 minutes. | ||||||
| 37 | respan-gateway | Runs with mocks | 92 / 100 | Rust | 994 | |
Open-source LLM gateway in Rust. One endpoint for OpenAI, Anthropic, Gemini and every other vendor. Any SDK, any model, any tool. What the test found: The pip-installed respan-gateway 0.3.0 runs as a binary serving HTTP on 127.0.0.1:8080 with all endpoints responding 200, and as a Python in-process gateway passing all 59 tests against a mock provider. 2 minutes. | ||||||
| 38 | Lynkr | Runs with mocks | 92 / 100 | JavaScript | 643 | |
Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI. What the test found: Server starts, responds to health checks with 200, and 1555 unit/integration tests pass across routing, compression, memory, caching, rate-limiting, and telemetry modules with mock credentials. 31 minutes. | ||||||
| 39 | sagify | Runs with mocks | 92 / 100 | Python | 442 | |
LLMs and Machine Learning done easily What the test found: sagify 0.25.4 installed in a Python 3.12 virtual environment. CLI responds to --help with 7 command groups (build, cloud, configure, init, llm, local, push) and all 63 existing pytest unit tests pass. 14 minutes. | ||||||
| 40 | grok2api-egress-enhancements | Runs with mocks | 92 / 100 | Go | 320 | |
Grok2API & CPA egress quality guard with proxy recovery, quarantine, migration, and operations UI What the test found: from_residential.py passes all 5 tests. quality_guard.py parses CLI args and validates bootstrap config. All Python sources compile. Patches are syntactically valid but target the grok2api tree. 4 minutes. | ||||||
| 41 | opencode-models-discovery | Runs with mocks | 92 / 100 | TypeScript | 222 | |
A universal OpenCode plugin for dynamic model discovery with flexible configuration for OpenAI-compatible providers. What the test found: npm run build passes all 343 tests under Node 22.22.0, the compiled plugin loads and is active in OpenCode v2.2.5, discovers two models from a local OpenAI-compatible mock, and completes an authenticated Hello chat turn using mock/alpha. 17 minutes. | ||||||
| 42 | proxy | Runs with mocks | 92 / 100 | TypeScript | 211 | |
Local-first LLM proxy that meters what every agent run costs and kills runaways before they drain your budget. Free, MIT. What the test found: RelayPlane proxy v1.9.64 builds from source, starts on port 4100/4101/4102, answers HTTP 200 on /health, CLI --help works, and 125 of 138 test files pass (1769 of 1832 tests). The 13 failing files are content/marketing-site/CI-workflow/test suites that require files from a monorepo structure not present in this... 19 minutes. | ||||||
| 43 | APIPark | Runs with mocks | 56 / 100 | TypeScript | 1,826 | |
Cloud native, ultra-high performance AI&API gateway, LLM API management, distribution system, open platform, supporting all AI APIs.🦄云原生、超高性能 AI&API网关,LLM API... What the test found: APIPark binary builds, starts on port 8288 with MySQL and Redis, serves HTTP 200 JSON API responses and embedded index.html, auto-creates all database tables, and passes 4 test packages. 57 minutes. | ||||||
| 44 | digiRunner-Open-Source | Could not verify | 75 / 100 | Java | 307 | |
digiRunner: Your API Gateway for Microservices What the test found: digiRunner compiles via Gradle bootJar, the standalone JAR starts and serves the admin UI on port 18080/18081 with H2 in-memory database and JWKS endpoint returning valid RSA256 keys. 10 minutes. | ||||||
| 45 | higress | Could not verify | 40 / 100 | Go | 9,812 | |
🤖 AI Gateway | AI Native API Gateway What the test found: Go controller binary and hgctl CLI build and respond to help; all Go unit tests pass (26 packages); WASM AssemblyScript SDK builds both debug and release wasm binaries. 15 minutes. | ||||||
| 46 | 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. | ||||||
| 47 | dario | Could not verify | 20 / 100 | JavaScript | 593 | |
One local endpoint that routes Claude Code, Cursor, Cline, Aider, Codex CLI and the SDKs through the Claude and ChatGPT plans you already pay for: seats first... What the test found: could not be verified; the log shows where it stopped. 4 minutes. | ||||||
| 48 | bitrouter | Could not verify | 20 / 100 | Rust | 239 | |
elastic inference for your agentic workloads What the test found: could not be verified; the log shows where it stopped. 37 minutes. | ||||||
| 49 | orbit | Could not verify | 10 / 100 | Python | 366 | |
Self-hosted AI gateway for private RAG, natural-language data access, and tool-calling agents. What the test found: could not be verified; the log shows where it stopped. 28 minutes. | ||||||
| 50 | agentgateway | Could not verify | 0 / 100 | Rust | 6,355 | |
Next Generation Agentic Proxy for AI Agents and MCP servers What the test found: could not be verified; the log shows where it stopped. 87 minutes. | ||||||
| 51 | agent-router | Could not verify | 0 / 100 | Go | 2,433 | |
Manages Unified Access to Generative AI Services built on Envoy Gateway What the test found: could not be verified; the log shows where it stopped. 87 minutes. | ||||||
| - | HiRoute | Not yet tested | - | Rust | 483 | - |
| - | yolorouter | Not yet tested | - | Go | 402 | - |
| - | 1flowbase | Not yet tested | - | Rust | 296 | - |
| - | DoulorCloud | Not yet tested | - | TypeScript | 283 | - |
| - | bella-openapi | Not yet tested | - | Java | 241 | - |
| - | aisix | Not yet tested | - | Rust | 231 | - |
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: 32 projects ran as-is, 11 with mocks, 8 could not be verified, 6 still waiting. Languages tested: Go, Java, JavaScript, Python, Rust, 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?
6 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
- API gateways (shares APIPark, CliRelay, agent-router, agentgateway, antirion, bitrouter, busbar, ccLoad, digiRunner-Open-Source, gpt-load, higress, krakend-ce, opencode-models-discovery with this list)
- self-hosted AI apps (shares CliRelay, Lynkr, antirion, ccLoad, gpt-load, oh-my-cpa, orbit, otari, respan-gateway with this list)
- open source coding agents (shares EnterpriseAgentFramework, Free-LLM, casbin-gateway, paritok-4b-v1, router with this list)
- observability tools (shares CPA-Manager-Plus, GoModel, future-agi with this list)
- AI agent frameworks (shares 9router, EnterpriseAgentFramework with this list)
- MCP servers (shares agentgateway, respan-gateway with this list)
- CI/CD tools (shares temps with this list)
- speech tools (shares orbit with this list)
- vector databases (shares orbit with this list)
- workflow automation tools (shares RabiRoute with this list)
- self-hosted dashboards (shares oh-my-cpa with this list)
- API clients
- CMS platforms
- VPN tools
- backup tools
- browser automation tools
- code editors
- Open source databases, installed and queried
- developer CLI tools
- 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
- project management tools
- screen recorders
- search engines
- self-hosted analytics
- static site generators
- uptime monitors
- open source video editors
- video players
- web scraping tools
- whiteboard tools
- wikis
- self-hosted Notion alternatives
- self-hosted git servers