AutoMaintainer

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Gecti
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

An Always-On Autonomous AI Software Engineering Team built with LangGraph, FastAPI, and Next.js that operates natively within your GitHub repositories.

README.md

title: AutoMaintainer
emoji: 🚀
colorFrom: blue
colorTo: indigo
sdk: docker
pinned: false

AutoMaintainer

An Always-On Autonomous AI Software Engineering Team

License: MIT
Python 3.10+
Next.js
FastAPI

AutoMaintainer is a revolutionary proof-of-concept that demonstrates an entirely autonomous, multi-agent software engineering team working natively inside your GitHub repositories.

Built with LangGraph, FastAPI, Next.js, and powered by Llama 3 (via Groq), this system doesn't just print code to a terminal—it brainstorms ideas, creates real GitHub Issues, writes code, submits Pull Requests, reviews the PRs, fixes its own bugs, and merges the code into your main branch.


Features

  • 5-Agent Hierarchy: Tasks are distributed across specialized agents (Architect, Visionary, Reviewer, Implementer, Maintainer).
  • Native GitHub Integration: Agents communicate through real GitHub Issues, PR Comments, and Git Branches.
  • Self-Correcting Iteration Loop: If the Maintainer AI rejects a PR, the Implementer AI reads the feedback and pushes a new commit to fix the bug!
  • Real-time Observability UI: A sleek, dark-mode React dashboard connected via WebSockets allows you to monitor the AI Crew as they work in real-time.
  • Blazing Fast: Powered by Groq's LPU inference, the entire cycle from Architecture to Merged PR can happen in under 20 seconds.

Quick Start

1. Prerequisites

2. Environment Setup

Clone the repository:

git clone https://github.com/PxA-Labs/AutoMaintainer.git
cd AutoMaintainer

Create a .env file in the root directory:

GROQ_API_KEY=your_groq_api_key_here
GITHUB_TOKEN=your_github_token_here
NEXT_PUBLIC_BACKEND_URL=http://your-custom-backend.com:8000  # Optional: For remote backends

3. Run the Backend (FastAPI + LangGraph)

Open a terminal and navigate to the backend directory:

cd backend
pip install -r requirements.txt
fastapi dev main.py

4. Run the Frontend (Next.js)

Open a new terminal and navigate to the dashboard directory:

cd dashboard
npm install
npm run dev

Note: In local development, the Next.js frontend runs on port 3000 and automatically proxies API traffic to the FastAPI backend running on port 8000. You can override this using the NEXT_PUBLIC_BACKEND_URL environment variable.


Usage

  1. Open http://localhost:3000 in your browser.
  2. In the sidebar under Configuration, click on the Target Repository and enter a repository you own (e.g., your-username/your-repo).
    • Note: Your GitHub Token must have push access to this repository!
  3. Click Start Agents.
  4. Watch the dashboard UI light up as the Architect scans your repo. Open your target repository on GitHub in another tab to watch the Issues and Pull Requests appear in real-time!

Architecture

Curious how it works under the hood? Read our Architecture Documentation to see how the 5-agent LangGraph topology operates.


Contributing

Want to add a new Agent or improve the dashboard? Check out our Contributing Guidelines.


License

This project is licensed under the MIT License.

Yorumlar (0)

Sonuc bulunamadi