Use Claude Code, Codex, Antigravity, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)

★ 70,507⑂ 10,947👁 467⑃ 1,105● 1,089▤ 139
PythonNOASSERTIONCreated 2026-01-28
Download: v6.19.32v6.19.32 ↓6.19.322026-11-15
+158
Daily
+3,040
Weekly
+11,711
Monthly
70,507
stars
10,947
forks
467
watchers
1,105
prs
1,089
issues
139
releases

README

Quick Start · Providers · Integrations · API · Phone · Manage




  Independent open-source project. Not affiliated with or endorsed by Anthropic. Claude and Claude Code are trademarks of Anthropic.


 Features

- Route any supported harness to models from any supported provider.
- 12 supported harnesses: Claude Code, Codex, Pi, OpenCode, Cline, Hermes, DeepSeek Harness, Grok Build, Muse Code, Aider, Antigravity CLI, or VS Code Chat.
  - Preserved native streaming, tool use, and interleaved thinking for maximum performance.
  - For Claude Code, route Fable, Opus, Sonnet, and Haiku to supported models.
- Use any model through any of four APIs: Anthropic Messages (/v1/messages), OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses), or Gemini (generateContent). See Use The API Directly.
- 61 supported providers, including free, paid, subscription, and local providers.
  - 1.3B+ free tokens per month.
  - FCC follows provider TOS and removes integrations if they stop being allowed.
- Use through the terminal, desktop apps (Codex App, Claude Desktop, and DeepSeek Desktop), IDE extensions (VS Code and JetBrains), your phone (Discord and Telegram), or your browser through native Code sessions.
  - Voice notes supported for Discord and Telegram using local Whisper or NVIDIA NIM.
- Up to 90% lower token usage using RTK and Headroom.
- State-of-the-art reliability features so you can keep coding through provider outages:
  - Automatic retries.
  - Configurable rate limits.
  - Configurable concurrency control.
  - Automatic model/provider fallback.
  - Automatic multi-API key fallback.

Free-tier availability and limits are controlled by each provider and may change.


  
  Claude Code running with FCC.



  
  A native Codex session in FCC's browser UI.


 Quick Start



 1. Install

macOS/Linux:

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


Windows PowerShell:

powershell
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1")))


When prompted, choose at least one coding agent and optionally enable RTK + Headroom token optimization for supported agents.

 2. Start FCC

 Windows

Open Free Claude Code from your desktop or Start menu.

 macOS

Open Free Claude Code from your desktop or Applications folder.

 Linux

Run:

bash
fcc-server


FCC opens the Admin UI after starting. On Windows and macOS, use the tray or
menu-bar icon to open Admin, restart, or quit. When using fcc-server, keep its
terminal open.



 3. Configure NVIDIA NIM

1. Create an API key at build.nvidia.com/settings/api-keys.
2. Open the Admin UI URL from the server log.
3. Open NVIDIA NIM in Providers, click Add key, paste the key, and click Save.
4. Leave MODEL on the default nvidia_nim/nvidia/nemotron-3-ultra-550b-a55b, or search the model dropdown and select another model.
5. Click Apply to save your model selection.

To pro

Top issues

Discussions

Latest release

v6.19.32 v6.19.32 2026-11-15
What's Changed
 patch: bump the dependencies group across 1 directory with 8 updates by @dependabot[bot] in https://github.com/Alishahryar1/free-claude-code/pull/2446


Full Changelog: https://github.com/Alishahryar1/free-claude-code/compare/v6.19.31...v6.19.32

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON