⚡ Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary. FREE now, FREE forever.

A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface.

AI Gateway: Claude Pro, Copilot, Gemini subscriptions → OpenAI/Anthropic/Gemini APIs. No API keys needed.

将 Z.ai Chat 代理为 OpenAI/Anthropic Compatible 格式，支持多模型列表映射、免令牌、智能处理思考链、图片上传等功能；Z.ai ZtoApi z2api ZaitoApi zai X-Signature 签名 GLM 4.5 v 4.6

duck.ai openai compatible api server

Home Assistant LLM integration for local OpenAI-compatible services (llamacpp, vllm, etc)

A high-performance, self-hosted Deno proxy that makes Fal.ai's powerful models (Flux, SDXL, etc.) compatible with the standard OpenAI image generation API. Use any OpenAI client seamlessly.

让 GLM-4.5 完美适配 Agent TARS 系统的高性能适配器 - 解决 toolcall 兼容性，提供智能 fallback，极低成本享受顶级 AI Agent 体验

🚀 Intelligent Ollama API proxy pool based on Cloudflare Workers - 基于 Cloudflare Workers 的智能 Ollama API 代理池，支持多账号轮询、自动故障转移、负载均衡和统一鉴权

A Docker-based OpenAI-compatible Text-to-Speech API server powered by Kyutai's TTS models with GPU acceleration support.

Complete guide to convert GitHub Copilot into an OpenAI-compatible API

An adapter to add OpenAI compatibility to your Hono app using the Vercel AI SDK

Gemini API: Rotate keys, break limits.

Spark-TTS Text-to-Speech with an OpenAI-compatible API, supporting seamless, unlimited-length generations. Includes a CLI interface.

The Universal LLM Gateway - Integrate ANY AI Model with One Consistent API

Poe API - OpenAI Compatible Wrapper

OpenAI-compatible bridge that exposes Codex CLI/SDK as /v1/chat/completions with multimodal + JSON schema

Go proxy API for Z.ai, compatible with OpenAI/Anthropic.

Expose agent CLIs (Codex, Cursor Agent, Claude Code, Gemini) as an OpenAI-compatible /v1 API gateway.

Local-first Copilot-style assistant powered by screen, mic, and clipboard input — fully offline, works with any LLM or OCR engine. Press a key, get results. No cloud, no lock-in.