
tetherto/qvacOpen-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS, Windows, Android, iOS.
TypeScript · JavaScript · C++★ 597↓ 202.1K/月2026年9月10日

ENTERPILOT/GoModelAI 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.
Go · JavaScript★ 1,1452026年9月11日

modelscope/FunASROpen-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python · C · HTML★ 20.4K2026年9月16日

Mindburn-Labs/helm-ai-kernelFail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
Go★ 552026年9月10日
Python★ 137↓ 11.5K/月2026年10月19日

waybarrios/vllm-mlxHigh-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
Python★ 1,626↓ 5,191/月2026年10月20日

HKUDS/nanobotUltra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
Python · TypeScript★ 48.3K2026年9月18日

ferro-labs/ai-gatewayUnified AI Gateway for 30+ LLMs (OpenAI, Anthropic, Bedrock, Azure etc) with Caching, Guardrails, A/B test & cost controls. Go-native Fastest & Scalable AI Gateway LiteLLM & Kong AI Gateway alternative.
Go · TypeScript★ 2562026年9月9日

tashfeenahmed/freellmapi7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.
TypeScript★ 27.4K↓ 6,354/月2026年9月20日

seakee/CPA-Manager-PlusA self-hosted CPA / CLIProxyAPI management panel and AI gateway observability dashboard for requests, usage, cost, quota, failures, and account health.
Go★ 3,3742026年9月12日

berkayturanci/ai-juryStdlib-only Python CLI that orchestrates universal AI agent providers (Claude Code, Codex, Antigravity, OpenRouter, DeepSeek, Groq, local models, Aider) into a multi-agent PR review jury — debate, verify, synthesize one verdict. Local-first, secure by default.
Python★ 8↓ 3,403/月2026年10月12日

BlockRunAI/blockrun-llm-tsTypeScript SDK for BlockRun — every frontier model behind one OpenAI-compatible client. Pay with a BlockRun API key or per-call in USDC. Smart routing picks the cheapest capable model. Zero rate limits.
TypeScript★ 3↓ 13.1K/月2026年9月10日

vladkesler/initrunnerDefine AI agent roles in YAML and run them anywhere: CLI, API server, or autonomous daemon
Python★ 41↓ 1,603/月2026年9月10日
TypeScript★ 131↓ 429.1K/月2026年9月8日

jin-bo/agentaoLocal-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.
Python★ 309↓ 2,631/月2026年10月18日

youssofal/MTPLX3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.
Python · Swift★ 2,329↓ 9,464/月2026年9月15日

Arthur-Ficial/apfelThe 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.
Swift · Python★ 6,3862026年9月16日

KevRojo/DulusDulus Ai — Free Agentic AI, Making Gemini web cappable of running bash commands in your terminal! [Gui, Web, Cli, Telegram, 2,000 MCP, 100K Skills . LiteLLM (100+ providers), local models via Ollama, /lang in 34 languages, Mesa Redonda, I create the first utility coin that can be used 100% as AI quota or Fuel, is called $Dulus
Python★ 358↓ 7,957/月2026年9月5日

arcships/aimuxUnified LLM access layer in Rust — one API for 325 AI providers. 统一 LLM 服务接入层:一套 API 接入 325 家 AI 服务商。
Rust★ 1952026年10月2日

verbatra/verbatraCLI, SDK, and local Studio dashboard to automate i18n translation across i18next, vue-i18n, next-intl, ngx-translate, XLIFF, YAML, Flutter ARB, and Java properties, using OpenAI, Anthropic, Gemini, DeepL, or an openai-compatible model.
TypeScript · MDX★ 2↓ 3,766/月2026年9月9日
TypeScript★ 65↓ 5,248/月2026年9月16日

ZahiriNatZuke/local-delegateMCP that delegates mechanical text tasks to a local OpenAI-compatible LLM endpoint to conserve Claude subscription quota.
Python★ 5↓ 1,283/月2026年9月14日

domondi1/inferrailSelf-hosted OpenAI/Anthropic-compatible gateway: give each AI agent run a dollar budget, enforced before the provider, with a payload-free per-run cost record.
Python★ 0↓ 4,824/月2026年10月5日
TypeScript★ 5↓ 7,724/月2026年9月18日

AIsa-team/cliCLI for the AISA unified AI infrastructure platform - access 70+ LLMs, web search, finance, Twitter, and video generation APIs
TypeScript · JavaScript★ 1↓ 2,101/月2026年9月12日

Tachion-Oy/robozPython framework for typed LLM agents with conditional tool chaining.
Python★ 0↓ 2,500/月2026年10月8日

dravr-ai/dravr-embacleRust library wrapping 12 AI CLI tools as pluggable LLM providers — with OpenAI API client, ACP headless mode, agent loop, MCP server, and OpenAI-compatible REST API
Rust★ 7↓ 2,813/月2026年9月18日
TypeScript★ 5↓ 47/月2026年9月12日

arikusi/deepseek-mcp-serverMCP server for DeepSeek V4 (v4-flash, v4-pro, 1M context): chat, reasoning, function calling, thinking mode, cost tracking. deepseek-chat/reasoner aliases supported.
TypeScript★ 24↓ 2,086/月2026年10月14日

hishamkaram/claude-code-routerA local gateway that routes Claude Code sessions to OpenAI-compatible and Anthropic-compatible models, with same-session switching and visible compatibility behavior.
Go★ 42026年9月10日