Claude Skill

open-gitagent/gitagent

GitAgent is a universal git-native AI agent framework. Identity, rules, memory, tools, and skills are all version-controlled files inside a git repo. Built with TypeScript.

Overview

Stars580
Forks112
LanguageTypeScript
Last pushed2026-07-01
Last synced2026-07-03
View on GitHub

Repository

Owneropen-gitagent
Repositorygitagent
Full nameopen-gitagent/gitagent
Repo ID1,172,540,122

Install this Skill

npm install -g @open-gitagent/gitagent

Registry

Typeopenclaw_skill
Quality score85/100
Verificationreadme_parsed
Last verified2026-06-09
Platforms
ClaudeOpenClaw
Capabilities
browsercode-reviewpdfmemorysearchterminalworkflowai-agentsanthropicassistant
Detected files
README.mddocsexamplespackage.jsontest
Config keys
OPENAI_API_KEYGITHUB_TOKENURLGIT_TOKENMY_API_KEYPACKAGE_JSON
Install methods
  • npm install -g @open-gitagent/gitagent
  • npm install -g @open-gitagent/voice
  • npm install -g @open-gitagent/gitagent@latest @open-gitagent/voice
  • npm install -g @open-gitagent/gitagent@latest
  • docker run --rm -p 16686:16686 -p 4318:4318 jaegertracing/all-in-one:latest

Summary

GitAgent is a universal, git-native AI agent framework where your agent's identity, rules, memory, tools, and skills are all stored as version-controlled files inside a git repository. Built with TypeScript, it enables seamless collaboration between human developers and AI agents through the familiar git workflow.

Chinese description

一个通用的原生Git AI代理框架。你的代理存在于Git仓库中——身份、规则、记忆、工具和技能都是版本控制的文件。

Key features

  • Git-native architecture: all agent configurations are version-controlled files
  • Modular skill system with versioned tools and rules
  • Persistent memory stored as git-tracked files
  • Built-in identity and rule management via repository structure
  • TypeScript-based for extensibility and type safety
  • Seamless integration with existing git workflows

Use cases

  • Automated code review and pull request management
  • Personal AI assistant for software development projects
  • Team collaboration with AI agents in shared repositories
  • Version-controlled AI agent behavior for reproducible experiments
  • Custom tool and skill development for specialized workflows

README excerpt

<p align="center"> <img src="./gitagent-logo.png" alt="GitAgent Logo" width="200" /> </p> <p align="center"> <img src="https://img.shields.io/npm/v/gitagent?style=flat-square&color=blue" alt="npm version" /> <img src="https://img.shields.io/badge/node-%3E%3D20-brightgreen?style=flat-square" alt="node version" /> <img src="https://img.shields.io/github/license/open-gitagent/gitagent?style=flat-square" alt="license" /> <img src="https://img.shields.io/badge/TypeScript-5.7-blue?style=flat-square&logo=typescript&logoColor=white" alt="typescript" /> </p> <h1 align="center">Gitagent</h1> <p align="center"> <strong>A universal git-native multimodal always learning AI Agent (TinyHuman)</strong><br/> Your agent lives inside a git repo — identity, rules, memory, tools, and skills are all version-controlled files. </p> <p align="center"> <a href="#one-command-install">Install</a> &bull; <a href="#quick-start">Quick Start</a> &bull; <a href="#sdk">SDK</a> &bull; <a href="#architecture">Architecture</a> &bull; <a href="#tools">Tools</a> &bull; <a href="#hooks">Hooks</a> &bull; <a href="#skills">Skills</a> &bull; <a href="#plugins">Plugins</a> </p> --- ## Why Gitagent? Most agent frameworks treat configuration as code scattered across your application. Gitagent flips this — **your agent IS a git repository**: - **`agent.yaml`** — model, tools, runtime config - **`SOUL.md`** — personality and identity - **`RULES.md`** — behavioral constraints - **`memory/`** — git-committed memory with full history - **`tools/`** — declarative YAML tool definitions - **`skills/`** — composable skill modules - **`hooks/`** — lifecycle hooks (script or programmatic) Fork an agent. Branch a personality. `git log` your agent's memory. Diff its rules. This is **agents

Topics

Explore more

Data from GitHub. Synced on 2026-07-03