Explore

Migrate your Python apps from the AzureOpenAI client with Chat Completions API to the OpenAI client with Responses API.

Official·Skill·MIT·★ 6·No key

Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.

Go·Apache-2.0·★ 429·No key

Open-source MCP server for safe, stateful AI-agent phone calls with OpenAI Realtime and Twilio.

Python·MIT·★ 298·No key

General-purpose agent in one static Go binary: console TUI, ACP server for editors, OpenAI-compatible API with embedded web UI, Telegram gateway, cron scheduler, swarm relay, remote mode. Rules, skill

Go·MIT·★ 176·No key

MindBridge is an AI orchestration MCP server that lets any app talk to any LLM — OpenAI, Anthropic, DeepSeek, Ollama, and more — through a single unified API. Route queries, compare models, get second

Node.js·MIT·★ 39·No key

The full featured self-hosted Codex gateway, for teams, agents and you

MCP·Link only·★ 229

MCP connector for Wassenger WhatsApp API: Send messages, summarize conversations, automate anything on WhatsApp using text or voice from your favorite AI client like ChatGPT, Claude, Gemini, OpenAI an

Node.js·MIT·★ 6·No key

Free LLM gateway: 22 LLM providers, 178 enabled chat routes, 431 cataloged chat models; keyless start when available.

Python·MIT·★ 127·No key

An MCP Server for chatGPT Chat Completions

Skill·MIT·★ 7·No key

MCP server for OpenAI API (chat, image, embeddings) via Ace Data Cloud.

Python·MIT·★ 1·Few stars·Needs a key

Your private, on-device personal AI assistant for macOS and Windows. Chat, create, search files, and connect tools with local models. Includes an OpenAI-compatible API. Opt-in Pro sees, remembers, ref

Skill·AGPL-3.0·★ 127·No key

Your AI agent needs your API keys. It doesn't need to see them. tokenstash writes keys straight into .env.local for Claude Code, Codex, Cursor and Gemini CLI. Paste each key once, in your browser, nev

Skill·MIT·★ 17·No key

Multi-Model chat, code review and analysis MCP Server for Claude Code

Python·MIT·★ 36·No key

WhatsApp MCP connector to any AI LLM client (Claude, ChatGPT, Github Copilot, Cline, OpenAI), powered by WaliChat API 🤖 🥳

Node.js·MIT·★ 1·Few stars·No key

OpenAI Codex CLI in a Docker image built on aicodebox, with an HTTP API, an OpenAI-compatible endpoint, an MCP server, a Telegram bot and a cron scheduler, in minimal or full-toolchain variants.

Docker·WTFPL·Few stars·No key

Agent-native macOS Keychain CLI for dev secrets. Never in .env files, shell history, or chat.

Skill·MIT·★ 6·No key

Local-first, self-hosted LLM workspace: Next.js chat, RAG over your PDFs, Ollama offline or cloud models via LiteLLM, MCP tools, and a plugin core. Runs entirely on your machine with Docker Compose.

Skill·MIT·★ 4·Few stars·No key

A local, privacy-first AI agent (Rust) that connects LLMs to your email, calendar, browser, code, and messages — 75+ tools, MCP/A2A support, Discord/Slack/iMessage channels, autonomous agent loop.

Skill·MIT·★ 6·No key

MCP server + public home for APIzone — independent real-time status monitoring for 200+ popular APIs (Stripe, OpenAI, AWS, GitHub, Twilio...). Read-only, no auth.

Hosted by author·MIT·Few stars·No key

One VS Code chat panel for all your coding agents: Claude Code, Codex, MiniMax and any OpenAI/Anthropic-compatible API.

Skill·MIT·★ 4·Few stars·No key

An MCP server for searching transcripts of Entra.Chat - Merill Fernando's Microsoft Entra podcast on YouTube. Ask your AI assistant about Entra ID features, community tools, and identity topics discus

Node.js·MIT·★ 2·Few stars·No key

Engram is a self-hostable AI memory layer. It sits between an application and an LLM provider, retrieves relevant user memories from pgvector, injects them into chat prompts, forwards the request, and

Skill·MIT·★ 4·Few stars·No key