Who is free-claude-code for?

Developers and students who already use terminal coding agents and want cheaper or free model access; they should be comfortable with API keys and a local server.

What can you build with free-claude-code?

Try Claude Code or Codex using a free NVIDIA NIM or OpenRouter model instead of a paid plan. Compare the same coding task across several models by switching them in one Admin page. Keep a long coding session going through a provider outage by configuring fallback models. Point Aider or Cline at a custom or local OpenAI-style endpoint. Send a voice note or Telegram message to a coding agent running on your machine.

Alishahryar1 /

free-claude-code

Local proxy that lets Claude Code, Codex, Aider and others run on free or cheap models

62.7k stars
6.3k stars since 3 Oct
Python
Updated today
Some experience
Coding agents & dev tools

Open on GitHub (opens in a new tab)

Coding agents like Claude Code or Codex normally talk to one company's models. This project sits in the middle as a local proxy. You add an API key for a provider such as NVIDIA NIM, OpenRouter or Groq, pick a model in a web Admin page, and the agent's requests go through the proxy to that model.

You install it with a script, start the server, then launch agents through wrappers such as fcc-claude, fcc-codex, fcc-pi or fcc-aider. You can also set an ordered list of fallback models, so if one provider fails after retries the proxy tries the next without making you restart the turn.

The README says streaming, tool use, images and thinking blocks keep working, and that the Opus, Sonnet and Haiku slots can be routed to different models. It also describes a browser UI for Codex sessions, voice notes through Whisper, and Discord or Telegram access. Free-tier limits belong to each provider and can change. The project says it is not affiliated with Anthropic, and the GitHub license field is unclear (the badge says AGPL v3), so check the license before relying on it.

What it does

Many providers, one model list
The README lists 59 providers covering free tiers, paid APIs, subscriptions and local models. You search one dropdown for a model, and can add custom API endpoints.
Eleven coding agents supported
Wrappers exist for Claude Code, Codex, Pi, OpenCode, Cline, Hermes, DeepSeek Harness, Grok Build, Muse Code, Aider and VS Code Chat.
Automatic fallback models
Set backup models in order. After retries run out, the proxy tries the next one. The README warns a failed request may use quota from more than one provider.
Token-saving options
Optional RTK filters terminal output, and five built-in optimizations handle things like quota probes, titles and filepath checks without calling a provider.
Browser, phone and voice access
Run Codex sessions in the browser, chat through Discord or Telegram, and send voice notes transcribed by local Whisper or NVIDIA NIM.

What you could build

Try Claude Code or Codex using a free NVIDIA NIM or OpenRouter model instead of a paid plan.
Compare the same coding task across several models by switching them in one Admin page.
Keep a long coding session going through a provider outage by configuring fallback models.
Point Aider or Cline at a custom or local OpenAI-style endpoint.
Send a voice note or Telegram message to a coding agent running on your machine.

Get started

Run the installer (the README suggests reading it first) and choose at least one coding agent. Start the server, open the Admin UI, paste a provider key such as NVIDIA_NIM_API_KEY, pick a model, click Apply, then launch an agent like fcc-claude. On Windows use the PowerShell installer; on macOS and Windows you open the app instead of running fcc-server.

curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh

fcc-server

fcc-claude

Commands are copied from the project's README. Read it on GitHub for the full setup.