Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching

Turn GitHub Copilot into OpenAI/Anthropic API compatible server. Usable with Claude Code!

LM inference server implementation based on *.cpp.

ThunderAI is a Thunderbird Addon that uses the capabilities of ChatGPT, Gemini, Claude or Ollama to enhance email management.

A text-to-speech and speech-to-text server compatible with the OpenAI API, supporting Whisper, FunASR, Bark, and CosyVoice backends.

Local first speech AI engine for transcription, TTS, and voice workflows.

Visual inference exploration & experimentation playground

Deploy open-source LLMs on AWS in minutes — with OpenAI-compatible APIs and a powerful CLI/SDK toolkit.

duck.ai openai compatible api server

A robust Node.js proxy server that automatically rotates API keys for Gemini and OpenAI APIs when rate limits (429 errors) are encountered. Built with zero dependencies and comprehensive logging.

An OpenAI Compatible API which integrates LLM, Embedding and Reranker. 一个集成 LLM、Embedding 和 Reranker 的 OpenAI 兼容 API

Demonstrates that Spring AI can be configured to work with OpenRouter so that you can work with multiple LLMs through a single Open AI compatible interface. Potentially helpful when evaluating the performance and quality of model responses.

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

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

OpenRouter model information

SDK to build Agents in rust. Build and manage complex, self-correcting agent teams. Launch multi-agent systems via configuration files or using an Agent Factory. It's the robust framework for orchestrating intelligent agents using open standards (MCP, A2A).

Poe API - OpenAI Compatible Wrapper

Nimbus is a zero-dependency local proxy that routes your IDE's AI requests to free LLM tiers (Groq, NIM, GitHub). It provides a unified OpenAI-compatible endpoint that uses speculative execution to dodge rate limits and auto-quarantine dead keys, guaranteeing the fastest possible generative AI—for free, forever.

Tool-based LLM integration with Zenodo via the Model Context Protocol (MCP)

🚀 Production-ready OpenAI-compatible API server with automatic multi-provider fallback & circuit breakers. Includes a lightweight Node.js library for direct integration