My Free Code — AI skill for Claude Code

My Free Code v0.8

**A multi-provider gateway for Claude Code and other coding agents.**

It is an independent implementation. It is **not affiliated with Anthropic**.

What v0.8 includes

Gateway protocols

• Anthropic Messages: /v1/messages
• Anthropic token counting: /v1/messages/count_tokens
• OpenAI Responses-compatible: /v1/responses
• model discovery: /v1/models
• health: /health
• local Admin UI: /admin
• authenticated Admin API: /api/admin/*

Agent features

• 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
• stable public model identity

Provider layer

The catalog contains the broad provider set used by the project:

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.

Provider entries are not fake claims of universal support: providers with unusual authentication/protocols require a dedicated adapter. The common OpenAI-compatible providers use the shared transport.

Coding-agent launcher layer

The architecture has launcher adapters for:

• Claude Code
• Codex
• Pi
• OpenCode
• Cline
• Hermes
• DeepSeek Harness
• Grok Build
• Muse Code

A launcher simply prepares the local proxy environment and delegates arguments to the installed client.

Architecture

             Coding Agents / IDEs
                      |
          +