Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
openmake_llm
MCP serversOpen-source, self-hosted AI workspace for local and open-weight LLMs with vLLM, LiteLLM, autonomous agents, MCP tools, deep research, artifacts, and BYOK.
git clone https://github.com/openmake/openmake_llm.git -
pegainfer
AI repositoriesPure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
git clone https://github.com/pegainfer-project/pegainfer.git -
gpt-image-2-6-api-gateway
PromptsOne OpenAI-compatible key for GPT Image 2.6 and other image models.
git clone https://github.com/fujc683/gpt-image-2-6-api-gateway.git -
Aivory
AI repositoriesSelf-hosted AI chat platform with multi-step tool calls, persistent Python sandbox, RAG, and Deep Research. Supports Claude, GPT, Gemini and any OpenAI-compatible provider.
git clone https://github.com/hjxwz123/Aivory.git -
Xenon
Agents & frameworksVerifiable AI coding agent harness / 可验证的 AI 编码代理:evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP · multi-model · Windows/CJK · listed in awesome-opensource-ai & Collabnix awesome-mcp-lists
git clone https://github.com/xianyu-sheng/Xenon.git -
SinoGate MCP Server
MCP serversUse Chinese LLMs through the SinoGate OpenAI-compatible API.
@sinogate/mcp@0.1.0 -
esp32-iphone-agent
MCP serversLet an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak.
git clone https://github.com/onehumanbeing/esp32-iphone-agent.git -
willdeep-cli
Agents & frameworks自托管 AI Coding Agent(Rust):常驻 Runtime 撑起终端 / 浏览器 / 手机三端;每行改动可追溯到具体 Agent 与工具调用,子 Agent 的活由退出码裁决,检查点回退、目标 token 预算与验收清单跨轮次跨重启累计,用量与反馈账本留在本地。接任意 OpenAI 兼容或 Anthropic 端点。Self-hosted auditable AI coding agent: per-line attribution, exit-code-verified sub-agents, restart-safe goal budgets, local usage and feedback ledgers.
git clone https://github.com/niuwoai/willdeep-cli.git -
grok-imagine-2.0 API (grokimagine2.0 / grok imagine 2.0): upload-image $0; default $0.015; region-edit $0.015. Model id, prompts settings, curl and Python examples over an OpenAI-c
git clone https://github.com/bx0idu7sqebwpgu8/grokimagine2.0-grok-imagine-2.0-prompts.git -
nihaixia-app
AI repositories倪海厦汉唐中医 AI 辅助诊断安卓客户端 · AI 讲义问答·六经辨证智能问诊、伤寒论 394 条、金匮 433 篇、322 首经方、465 味本草、408 穴位、1257 例倪师医案、本草讲稿 335 篇、针灸讲稿 72 篇|可选「问倪师AI」:本地讲义检索 + 自配模型,默认关闭零联网;子午流注 / 灵龟八法 / 五运六气 / 小六壬 / 梅花易数 / 紫微斗数 / 易经 64 卦 / 八字四柱 / 周公解梦 / 小儿关煞 / 每日黄历 / 节气养生 / 玉匣记;离线优先、数据全本地、无需注册、无广告无内购无追踪,Flutter / Dart + Apache 2.0 开源免费。
git clone https://github.com/jangviktor-web/nihaixia-app.git -
self-hosted-ai-stack
AI repositoriesDeploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings, transcription, text-to-speech and MCP tools. Powered by Ollama, LiteLLM, AnythingLLM and more. Local-first with auto-configured authentication, lightweight stacks, optional HTTPS and NVIDIA GPU support. MIT licensed. Multi-arch: amd64, arm64.
git clone https://github.com/hwdsl2/self-hosted-ai-stack.git -
2kw.ai
MCP serversEU-hosted AI platform: OpenAI-compatible LLM gateway, document extraction, transcription, agents.
@2kw/ai-mcp-server@8.0.3 -
Requesty
Public APIsOpenAI compatible LLM router for 600+ models, with a free tier for free models
-
Voxell Forge
Public APIsOpenAI-compatible text embeddings API, free-forever model with no credit card required
-
Opper
Public APIsEU-hosted OpenAI-compatible gateway to 700+ models from 50+ providers, with free models
-
BigMoeOnEdge
AI repositoriesRun MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
git clone https://github.com/Helldez/BigMoeOnEdge.git -
proxyllm-mcp
MCP serversOpenAI-compatible LLM gateway: models, savings math, key provisioning, autonomous email-OTP signup
proxyllm-mcp@1.0.2 -
mcp-computeflux
MCP serversOpenAI-compatible multi-model inference via ComputeFlux (Polkadot testnet, TEE-verifiable). stdio.
https://github.com/computeflux2026isgod/mcp-computeflux/releases/download/v1.0.0.0/send_mcp-computeflux.mcpb -
mediamcp
MCP serversGenerate and edit images and video via OpenRouter or any OpenAI-compatible API.
mediamcp@0.3.0 -
Hubris
MCP serversOpenAI-compatible LLM gateway for Russia: 500+ models, ruble pricing, balance, chat.
hubris-mcp@0.1.1 -
ModelLens
MCP serversSee which models actually work: probe, rank and recommend across OpenAI-compatible gateways.
modellens-mcp@0.1.3 -
Gridline
MCP serversFine-tune, evaluate and batch open models through Gridline's OpenAI-compatible API.
@gridlinegpu/mcp@0.1.2 -
ObsidianRAG
AI repositoriesAsk questions about your Obsidian notes using local AI. Privacy-first RAG with Ollama, LM Studio, or any OpenAI-compatible server. Obsidian plugin + Docker + PyPI.
git clone https://github.com/Vasallo94/ObsidianRAG.git -
Token Counter
MCP serversCounts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.