Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

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

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

AI gateway written in Go. Lightweight unified OpenAI-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI & Ollama. LiteLLM alternative with observability, guardrails, streaming, costs and usage tracking.

FreeTheAi (Free The AI): free OpenAI-compatible AI API with 50+ models, Discord key signup, streaming, tools, images, Messages, and Responses. No credit card.

Self-hosted Personal AI + agent runtime in .NET (NativeAOT-friendly)

Voice AI runtime. Local first transcription, speaker diarization, TTS, and voice cloning with an OpenAI compatible API.

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

LM inference server implementation based on *.cpp.

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

Локальный API-прокси для Qwen AI с поддержкой сохранения контекста диалогов и управления сессиями через REST API

Open-source local AI client and coding agent for DeepSeek, Qwen, ChatGPT and EconomyOS with memory, voice, browser tools, OpenAI/Anthropic-compatible APIs and VS Code.

duck.ai openai compatible api server

Visual inference exploration & experimentation playground

A curated list of permanently free LLM APIs — with rate limits, OpenAI SDK compatibility, available SDKs, speed tiers, and free model lists. No trial credits. No time-limited promos. No credit card required.

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

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.

Paused Codex App auth-split proxy experiment; future work would need a Responses-to-Chat-Completions adapter.

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

Run local LLMs on Apple Silicon with an OpenAI-compatible API powered by MLX.