openai-compatible

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.

Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.

Open-source GEO content engineering and multi-site distribution platform with AI quality inspection, illustrated admin help, hosted sites, browser-assisted publishing, and signed updates.

A self-hosted CPA / CLIProxyAPI management panel and AI gateway observability dashboard for requests, usage, cost, quota, failures, and account health.

FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM providers.

Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, Anthropic- & Gemini-compatible APIs. Zero-dependency self-hosted reverse proxy for Claude Code, Cline & Cursor. 把 Windsurf/Devin 云端 100+ 模型变成三套兼容 API。

The fastest way to run Qwen 3.8 Flash Next and Qwen 3.8 27B on a Mac: 125 tok/s in OpenCode on an M5 Max. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

Self-hosted LLM router with a managed safety net. OpenAI-compatible. BYOK. Single-workspace. Streaming. For more advanced routing choose hosted OrcaRouter

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

OpenClaw alternative in your pocket

Standalone CliProxyAPI usage tracker with SQLite persistence and built-in dashboard.

AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative with observability, guardrails, streaming, cost tracking, intelligent routing, sticky sessions, failover, real-time logs and usage tracking. Prod ready.

Govern, Observe, Direct - a real-time control room for agent societies

⚡ Self-hostable YesCaptcha-compatible captcha solver built with FastAPI, Playwright, and OpenAI-compatible multimodal models.

A test runner for agentskills.io-style AI agent skills