Refact.ai
- ide
Open-source AI Agent for VS Code and JetBrains that autonomously solves coding tasks end-to-end.
About
What is Refact.ai?
Refact.ai is an open-source AI software development agent that handles engineering tasks end-to-end. It runs as a plugin for VS Code and JetBrains IDEs, designed to help developers automate complex, multi-step tasks by deeply understanding their codebases.
How to use Refact.ai?
Install the plugin for VS Code or JetBrains from the official marketplace. For self‑hosted use, run the server via Docker or pip install ., then set the inference URL to http://127.0.0.1:8008 in the plugin settings (VS Code: Extensions > Refact.ai Assistant > Settings > Address URL; JetBrains: Settings > Tools > Refact.ai > Advanced > Inference URL).
Key features of Refact.ai
- Unlimited context‑aware auto‑completion using RAG.
- Integrated in‑IDE chat that understands your code.
- Connects with GitHub, GitLab, PostgreSQL, MySQL, Pdb, Docker, and shell.
- Supports state‑of‑the‑art models like Claude 3.7 Sonnet, GPT‑4o, and o3‑mini.
- Bring Your Own Key (BYOK) for external LLMs.
- Fully on‑premise deployment for code privacy.
Use cases of Refact.ai
- Generate code from natural language prompts.
- Refactor code for better quality and readability.
- Debug errors with AI‑assisted detection and fixes.
- Generate unit tests and docstrings automatically.
- Create or update code documentation and conduct code reviews.
FAQ from Refact.ai
How do I install Refact.ai?
You can install the server via pip install . or by running a pre‑built Docker container. For IDE integration, download the plugin for VS Code or JetBrains from their respective marketplaces.
Is Refact.ai free?
Yes, Refact.ai is completely free and open‑source, with unlimited auto‑completion and chat features.
Can I use my own API keys for external LLMs?
Absolutely. Refact.ai supports Bring Your Own Key (BYOK), allowing you to use your own API keys for models like Claude, GPT‑4o, and others.
What IDEs are supported?
Refact.ai works with VS Code and JetBrains IDEs (e.g., IntelliJ IDEA, PyCharm, WebStorm).
What models does Refact.ai support?
It supports a wide range of state‑of‑the‑art models including Claude 3.7 Sonnet, GPT‑4o, o3‑mini, and over 25 programming languages. See the full list in the documentation.
Details
- Author
- smallcloudai
- Category
- ide
- Repository
- smallcloudai/refact
<a name="readme-top"></a>
<div align="center">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://docs.refact.ai/_astro/logo-dark.CCzD55EA.svg">
<source media="(prefers-color-scheme: light)" srcset="https://docs.refact.ai/_astro/logo-light.CblxRz3x.svg">
<!-- Fallback if neither preference is set -->
<img alt="Refact.ai logo" src="https://docs.refact.ai/_astro/logo-dark.CCzD55EA.svg" width="200">
</picture>
<h1 align="center">Refact - Open Sourced AI Software Development Agent</h1>
</div>
<div align="center">
<a href="https://github.com/smallcloudai/refact/stargazers"><img src="https://img.shields.io/github/stars/smallcloudai/refact?style=for-the-badge&color=blue" alt="Stargazers"></a>
<a href="https://discord.gg/Kts7CYg99R"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
<a href="https://docs.refact.ai"><img src="https://img.shields.io/badge/documentation-blue?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
</div>
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
- 🤖 Which Tasks Can Refact Help You With?
- ⚙️ QuickStart
- 🐳 Running Refact Self-Hosted in a Docker Container
- 🔌 Getting Started with Plugins
- 📖 Documentation
- 🥇 Contribution
- 🎉 Join the Community
🚀 Core Features and Functionality
✅ Unlimited accurate auto-completion with context awareness – Powered by Qwen2.5-Coder-1.5B, utilizing Retrieval-Augmented Generation (RAG).
✅ 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.
✅ 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.
🤖 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:
``
bash
pip install .
`
For GPU with CUDA capability >= 8.0 and flash-attention v2 support:
bash
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 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 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.
