my-free-code

Open-source multi-provider AI gateway for Claude Code and other coding agents, with model routing, streaming, tools, reasoning, fallbacks, and local model suppo

What is my-free-code?

Open-source multi-provider AI gateway for Claude Code and other coding agents, with model routing, streaming, tools, reasoning, fallbacks, and local model support

Overview of my-free-code

What it is

My Free Code v0.8 is an open-source multi-provider AI gateway designed for Claude Code and other coding agents. It is an independent implementation and is not affiliated with Anthropic. The gateway supports multiple wire protocols, model routing, streaming, tool calls, reasoning pass-through, fallbacks, and local model support.

Key features

  • Supports Anthropic Messages (/v1/messages), token counting (/v1/messages/count_tokens), OpenAI Responses-compatible (/v1/responses), model discovery (/v1/models), health (/health), local Admin UI (/admin), and authenticated Admin API (/api/admin/*).
  • Agent features include streaming SSE, tool definitions and tool calls, tool results, images, reasoning/thinking metadata pass-through, Claude tier routing (Fable/Opus/Sonnet/Haiku), no-thinking gateway IDs, ordered model fallback, provider health backoff, per-provider concurrency, rate-window control, and stable public model identity.
  • Provider catalog includes NVIDIA NIM, OpenRouter, Groq, OpenAI, xAI, QwenCloud, Together, DeepInfra, SiliconFlow, Nebius, Chutes, Featherless, ZenMux, W&B Inference, Azure OpenAI, Google AI Studio, Google Vertex, DeepSeek, Mistral, Codestral, OpenCode Zen, OpenCode Go, Vercel AI Gateway, Amazon Bedrock, Hugging Face, Cohere, GitHub Models, Wafer, Kimi, Kimi Code, MiniMax, Cerebras, SambaNova, Kilo, Fireworks, Novita, Cloudflare Workers AI, Z.ai, TokenRouter, NaraRoute, Poolside, LLM7, Ollama Cloud, LM Studio, llama.cpp, and Ollama.
  • Coding-agent launcher adapters for Claude Code, Codex, Pi, OpenCode, Cline, Hermes, DeepSeek Harness, Grok Build, and Muse Code.
  • Architecture separates wire protocols, routing, provider code, CLI adapters, and optional messaging.

Use cases

  • Running Claude Code or other coding agents with multi-provider model routing and fallback.
  • Using local models (Ollama, LM Studio, llama.cpp) alongside cloud providers.
  • Testing and developing coding agents with a local gateway that supports reasoning, tools, and streaming.
  • Managing provider concurrency, rate limits, and health checks for production agent workflows.

Getting started

Python 3.11+ required.bashpython -m venv .venvWindows:powershell.venvmacOS/Linux:bashsource .venv/bin/activatepython -m pip install -r requirements.txtcp .env.example .envStart:bashpython -m my_free_codeDefault address: http://127.0.0.1:8082

License and pricing

License: MIT. Pricing: open source (free).

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/hkqrmy-free-code.svg)](https://yunodb.com/tools/hkqrmy-free-code?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/hkqrmy-free-code?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/hkqrmy-free-code.svg" alt="Featured on YunoDB" height="20"></a>