CodebuffAI /freebuff

The free coding agent

★ 14,181⑂ 1,521👁 82⑃ 896● 706▤ 9
TypeScriptApache-2.0Created 2024-07-09freebuff.com
Download: Codecane v1.0.420-beta.185 (Staging)v1.0.420-beta.185 ↓1852025-10-21
+17
Daily
+237
Weekly
+708
Monthly
14,181
stars
1,521
forks
82
watchers
896
prs
706
issues
9
releases

README

Freebuff

English | 简体中文

Five free AI products for coding, building, and research. No subscription, credits, or API key required.

Freebuff brings specialized agents and a choice of leading models to your terminal, desktop, browser, and GitHub repositories. Text ads support access to the included models.

 Choose your Freebuff

| Product              | What it does                        | Get started                                                           |
| -------------------- | ----------------------------------- | --------------------------------------------------------------------- |
| Freebuff Desktop | Run parallel agents locally         | Download for macOS, Windows, or Linux |
| Freebuff CLI     | Code from your terminal             | Install the CLI                           |
| Freebuff Web     | Build and ship full-stack apps      | Build an app                              |
| Freebuff Cloud   | Run agents on any GitHub repository | Connect a repository                    |
| Freebuff Chat    | Research and think with AI          | Start a chat                             |

The Freebuff apps for iOS and Android let you follow and continue your chats from your phone, including chats running on your computer while Freebuff Desktop is open: get the mobile app.

 Quick start

Run Freebuff in any project from your terminal:

bash
npm install -g freebuff
cd ~/my-project
freebuff


Then describe what you want. Freebuff finds the relevant files, makes changes, and runs the checks that matter for your project.

 Models

Freebuff includes a curated model catalog. The regular picker currently offers:

| Model                       | Access                  | Best for                                                          |
| --------------------------- | ----------------------- | ----------------------------------------------------------------- |
| DeepSeek V4.1 Flash     | Full and limited access | Fast coding and tool use at a steady speed, 1M context; the default at limited access with a paid plan |
| DeepSeek V4.1 Flash Slow | Full and limited access | The same model streamed more slowly, for fewer hours; the default at limited access without a plan, and in Chat mode |
| Solar Mini 4            | Full and limited access | Upstage's fast, compact model; 500K context, text only |
| Solar Pro 4             | Full and limited access | Upstage's larger, stronger model; 500K context, text only |
| Beam 1.0, Glyph Cluster and Nemotron 3.5 Lightning | Full and limited access | Free experimental models that use none of your hours; 256K context |
| DeepSeek V4.1 Flash Fast | Full and limited access | The same DeepSeek model at full speed; the default at full access |
| GPT-6 Luna              | Full access; paid plans on newer accounts | Strong all-around with native images; 1M context |
| Muse Spark 1.3          | Paid plans              | Meta's agentic coding model; 1M context. When it is busy or unavailable, it answers on DeepSeek V4.1 Fl

Top issues

Discussions

Latest release

Codecane v1.0.420-beta.185 (Staging) v1.0.420-beta.185 Pre-release 2025-10-21
Codecane v${VERSION} (Staging)

⚠️ This is a staging build intended for internal testing.

 Included Binaries
- codecane-linux-x64.tar.gz
- codecane-linux-arm64.tar.gz
- codecane-darwin-x64.tar.gz
- codecane-darwin-arm64.tar.gz
- codecane-win32-x64.tar.gz

After downloading, extract the tarball, add the binary to your PATH, and run codecane --help for usage.

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