Sponsored by Deepsite.site

Refact.ai

Created By
smallcloudai9 months ago
Open-source AI Agent for VS Code and JetBrains that autonomously solves coding tasks end-to-end.
Content

Refact.ai logo

Refact - Open Sourced AI Software Development Agent

Stargazers Join our Discord community Check out the documentation

Refact Agent is a free, open-source AI Agent that handles engineering tasks end-to-end. It deeply understands your codebases and integrates with your tools, databases, and browsers to automate complex, multi-step tasks.

🚀 Seamless Integration with Your Workflow

Refact Agent works effortlessly with the tools and databases you already use:

  • 📁 Version Control: GitHub, GitLab
  • 🗄️ Databases: PostgreSQL, MySQL
  • 🛠️ Debugging: Pdb
  • 🐳 Containerization: Docker

⚡ Why Choose Refact Agent?

  • Deploy On-Premise: Maintain 100% control over your codebase.
  • 🧠 Access State-of-the-Art Models: Supports Claude 3.7 Sonnet, GPT-4o, o3-mini, and more.
  • 🔑 Bring Your Own Key (BYOK): Use your own API keys for external LLMs.
  • 💬 Integrated IDE Chat: Stay in your workflow, no need to switch between tools!
  • Free, Unlimited, Context-Aware Auto-Completion: Code faster with smart AI suggestions.
  • 🛠️ Supports 25+ Programming Languages: Python, JavaScript, Java, Rust, TypeScript, PHP, C++, C#, Go, and many more!

📜 View Full List of Supported Models

📢 Using AI for work? Let’s bring it to your company!

Fill out this form — Our AI Agent will be tailored to your company’s data, learning from feedback, and helping organize knowledge for better collaboration with your team.

📚 Table of Contents

🚀 Core Features and Functionality

Unlimited accurate auto-completion with context awareness – Powered by Qwen2.5-Coder-1.5B, utilizing Retrieval-Augmented Generation (RAG).

auto-completion

Integrated in-IDE Chat – AI deeply understands your code and provides relevant, intelligent answers.

Integrated with Tools – Works with GitHub, GitLab, PostgreSQL, MySQL, Pdb, Docker, and shell commands.

integrations

State-of-the-Art Models – Supports Claude 3.7 Sonnet, GPT-4o, o3-mini, and more.

Bring Your Own Key (BYOK) – Use your own API keys for external LLMs.

BYOK

🤖 Which Tasks Can Refact Help You With?

  • 🏗 Generate code from natural language prompts (even with typos).

  • 🔄 Refactor code for better quality and readability.

  • 📖 Explain code to quickly understand unfamiliar code.

  • 🐞 Debug code to detect and fix errors faster.

  • 🧪 Generate unit tests for reliable code.

  • 📌 Code Review with AI-assisted suggestions.

  • 📜 Create Documentation to keep knowledge up to date.

  • 🏷 Generate Docstrings for structured documentation.

⚙️ QuickStart

You can install the Refact repository without Docker:

pip install .

For GPU with CUDA capability >= 8.0 and flash-attention v2 support:

FLASH_ATTENTION_FORCE_BUILD=TRUE MAX_JOBS=4 INSTALL_OPTIONAL=TRUE pip install .

🐳 Running Refact Self-Hosted in a Docker Container

The easiest way to run the self-hosted server is using a pre-built Docker image.
See CONTRIBUTING.md for installation without a Docker container.

🔌 Getting Started with Plugins

  1. Download Refact for VS Code or JetBrains.
  2. Set up a custom inference URL:
    http://127.0.0.1:8008
    
  3. Configure the plugin settings:
    • JetBrains: Settings > Tools > Refact.ai > Advanced > Inference URL
    • VSCode: Extensions > Refact.ai Assistant > Settings > Address URL

📖 Documentation

For detailed guidance and best practices, check out our documentation.

🥇 Contribution

Want to contribute to our project? We're always open to new ideas and features!

  • Check out GitHub Issues – See what we're working on or suggest your own ideas.
  • Read our Contributing Guide – Check out Contributing.md to get started.

Your contributions help shape the future of Refact Agent! 🚀

🎉 Join the Community

We're all about open-source and empowering developers with AI tools. Our vision is to build the future of programming. Join us and be part of the journey!

📢 Join our Discord server – A community-run space for discussion, questions, and feedback.

Made with ❤️ by developers who automate the boring, so you can focus on building the future.

Recommend Clients
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
WindsurfThe new purpose-built IDE to harness magic
Tavily Mcp
Playwright McpPlaywright MCP server
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Serper MCP ServerA Serper MCP Server
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
CursorThe AI Code Editor
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
ChatWiseThe second fastest AI chatbot™
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
DeepChatYour AI Partner on Desktop
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
Amap Maps高德地图官方 MCP Server
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors