Coding & Developmentβ¨geminiπ€claudeπ¬gptπuniversal
Code Buddy
Open-source multi-provider AI coding agent: terminal TUI, Electron desktop cockpit (Cowork), and a 24/7 autonomous multi-AI fleet that runs free-first on local Ollama. 15 LLM providers (Claude, GPT, Gemini, Grok), ~110 tools, voice + vision companion, MCP.
Quick Start
Install this Skill
npx skills add phuetz/code-buddy<div align="center">
<img src="https://img.shields.io/badge/π€-Code_Buddy-blueviolet?style=for-the-badge&labelColor=1a1a2e" alt="Code Buddy"/>
# Code Buddy
### The open-source AI coding agent that runs **free, on your own machine**
<p align="center">
<a href="https://www.npmjs.com/package/@phuetz/code-buddy"><img src="https://img.shields.io/npm/v/@phuetz/code-buddy.svg?style=flat-square&color=ff6b6b&label=version" alt="npm version"/></a>
<a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-feca57.svg?style=flat-square" alt="License: MIT"/></a>
<a href="https://nodejs.org"><img src="https://img.shields.io/badge/node-%3E%3D18.0.0-54a0ff?style=flat-square&logo=node.js" alt="Node Version"/></a>
<a href="https://www.typescriptlang.org/"><img src="https://img.shields.io/badge/TypeScript-5.3-5f27cd?style=flat-square&logo=typescript" alt="TypeScript"/></a>
<a href="https://deepwiki.com/phuetz/code-buddy/"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"/></a>
</p>
<p align="center">
<a href="https://github.com/phuetz/code-buddy/stargazers"><img src="https://img.shields.io/github/stars/phuetz/code-buddy?style=flat-square&logo=github&color=feca57&label=Star" alt="GitHub stars"/></a>
<img src="https://img.shields.io/badge/Tests-27K%2B-00d26a?style=flat-square&logo=jest" alt="Tests"/>
<img src="https://img.shields.io/badge/v1.2.0-GA-blueviolet?style=flat-square" alt="Version 1.2.0 GA"/>
</p>
<br/>
Watch a **local model reason on screen, then use real tools to do the work** β no cloud, no API bill, `~$0`. Or bring any of **15 providers** (Claude, GPT, Grok, Gemini, β¦) with automatic failover. From your terminal, a desktop app, your phone, or a 24/7 service. No lock-in.
<p align="center">
<a href="docs/qa/code-buddy-studio/cowork-demo-moneyshot.mp4"><img src="docs/qa/code-buddy-studio/cowork-demo-moneyshot.gif" alt="A local model reasons, then creates a file β for ~$0.0001" width="760"/></a>
<br/>
<sub>A <b>local</b> model reasons, then uses a tool to create a real file β <code>~$0.0001</code>, no cloud. <a href="cowork/readme.md#demo">More demos β</a></sub>
</p>
- π **Free & local-first** β runs entirely on local **Ollama (`$0`)**, any of **15 providers** with auto-failover, or a flat-fee **ChatGPT Plus/Pro** login (no API metering).
- π§ **Reasoning you can watch** β local models think step-by-step on screen, then call tools to act. See the [live captures](cowork/readme.md#demo).
- π οΈ **~110 tools** β edit, shell, web search, browser, PDFs/Office, a skills marketplace, and MCP connectors to extend it.
- π₯οΈ **Runs everywhere** β terminal TUI, the **Cowork** desktop app, an HTTP/WebSocket server, your phone, or a 24/7 background service β one core engine.
- π€ **Multi-AI Fleet** β peers observe each other live and call each other's models & read-only tools (`peer.chat` / `peer.tool.invoke`) across your network.
- ποΈ **Personal companion** *(optional)* β bidirectional voice, opt-in camera/presence, persistent memory, and 20+ messaging channels.
> **Don't take our word for it β [see it work, reproduce it yourself β
](docs/proof.md).** Every headline claim above, with the exact command and the real `$0` output (local model writes code + a passing test, goal mode, the desktop app, the autonomous fleet loop).
<br/>
[Live site β](https://phuetz.github.io/code-buddy/) Β·
[Proof β
](docs/proof.md) Β·
[Quick Start](#quick-start) Β·
[In action](#in-action) Β·
[Features](#features) Β·
[FAQ](docs/faq.md) Β·
[Docs](#documentation) Β·
[Contributing](#contributing)
</div>
---
## What is Code Buddy?
An open-source, multi-provider AI coding agent with a terminal UI, an HTTP/WebSocket server, and the **Cowork** desktop app β all on one core engine. It reads files, writes code, runs commands, opens PRs, and plans complex tasks across **15 LLM providers** with automatic failover and per-provider circuit breakers. With `buddy login`, a ChatGPT Plus / Pro subscription becomes the flat-fee brain of the whole system β no API keys, no per-token metering. An optional companion layer adds voice, durable memory, opt-in camera perception, and 24/7 background operation.
---
## In action
**It writes the code *and* the test, then runs it β `$0`.** Hand Code Buddy a task in the terminal; here Grok (a flat-fee subscription, no API key) writes FizzBuzz + a test and runs it green β then a human re-runs the test to confirm. Unedited:
<p align="center">
<img src="docs/assets/coding-demo.gif" alt="Code Buddy writes fizzbuzz.mjs and a test on Grok, runs it, and the test passes β $0, no API key" width="760"/>
</p>
**Free local AI, with the reasoning on screen.** A local Ollama model (`qwen3.6:35b-a3b`) thinks through a task, then *uses tools* to do it β no cloud, ~`$0.0001`. Unedited captures from the Cowork desktop app:
<table>
<tr>
<td width="50%" align="center">
<a href="docs/qa/code-buddy-studio/cowork-demo-chat.mp4"><img src="docs/qa/code-buddy-stud
... (truncated)Repository
20stars
4forks
Details
Related Skills
More coding & development skills you might like
Reticle
Coding & DevelopmentAI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.
π€claudeπuniversal
1.2k
190
View
agentscope-java
Coding & DevelopmentExpert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or Java agent development. Specializes in non-blocking code, tool integration, hooks, pipelines, and production-ready agent applications.
πuniversal
6.0k
1.5k
View
ospec
Coding & DevelopmentDocument-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
β¨geminiπ€claudeπ¬gptπuniversal
524
34
View
misakanet-failure-memory
Coding & Developmentπ A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. | https://misakanet.org
π€claudeβ¨οΈcursorπuniversal
424
158
View