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.
Refact Agent works effortlessly with the tools and databases you already use:
- π Version Control: GitHub, GitLab
- ποΈ Databases: PostgreSQL, MySQL
- π οΈ Debugging: Pdb
- π³ Containerization: Docker
- β Deploy On-Premise: Maintain 100% control over your codebase.
- π§ Access State-of-the-Art Models: Supports Claude 3.7 Sonnet, GPT-4o, o3-mini, and more.
- π Bring Your Own Key (BYOK): Use your own API keys for external LLMs.
- π¬ Integrated IDE Chat: Stay in your workflow, no need to switch between tools!
- β‘ Free, Unlimited, Context-Aware Auto-Completion: Code faster with smart AI suggestions.
- π οΈ Supports 25+ Programming Languages: Python, JavaScript, Java, Rust, TypeScript, PHP, C++, C#, Go, and many more!
π View Full List of Supported Models
π’ Using AI for work? Letβs bring it to your company!
Fill out this form β Our AI Agent will be tailored to your companyβs data, learning from feedback, and helping organize knowledge for better collaboration with your team.
- π Core Features and Functionality
- π€ Which Tasks Can Refact Help You With?
- βοΈ QuickStart
- π³ Running Refact Self-Hosted in a Docker Container
- π Getting Started with Plugins
- π Documentation
- π₯ Contribution
- π Join the Community
β Unlimited accurate auto-completion with context awareness β Powered by Qwen2.5-Coder-1.5B, utilizing Retrieval-Augmented Generation (RAG).
β Integrated in-IDE Chat β AI deeply understands your code and provides relevant, intelligent answers.
β Integrated with Tools β Works with GitHub, GitLab, PostgreSQL, MySQL, Pdb, Docker, and shell commands.
β State-of-the-Art Models β Supports Claude 3.7 Sonnet, GPT-4o, o3-mini, and more.
β Bring Your Own Key (BYOK) β Use your own API keys for external LLMs.
-
π Generate code from natural language prompts (even with typos).
-
π Refactor code for better quality and readability.
-
π Explain code to quickly understand unfamiliar code.
-
π Debug code to detect and fix errors faster.
-
π§ͺ Generate unit tests for reliable code.
-
π Code Review with AI-assisted suggestions.
-
π Create Documentation to keep knowledge up to date.
-
π· Generate Docstrings for structured documentation.
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 .
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.
- Download Refact for VS Code or JetBrains.
- Set up a custom inference URL:
http://127.0.0.1:8008
- Configure the plugin settings:
- JetBrains: Settings > Tools > Refact.ai > Advanced > Inference URL
- VSCode: Extensions > Refact.ai Assistant > Settings > Address URL
For detailed guidance and best practices, check out our documentation.
Want to contribute to our project? We're always open to new ideas and features!
- Check out GitHub Issues β See what we're working on or suggest your own ideas.
- Read our Contributing Guide β Check out
Contributing.md
to get started.
Your contributions help shape the future of Refact Agent! π
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!
π’ Join our Discord server β A community-run space for discussion, questions, and feedback.
Made with β€οΈ by developers who automate the boring, so you can focus on building the future.