Aider
Git-integrated pair programming with surgical edits and undo.
About
Git-integrated pair programming with surgical edits and undo. Found in: owainlewis/awesome-artificial-intelligence
Details
Aider is an open-source AI pair programming tool that runs in your terminal, enabling collaboration with large language models (LLMs) to start new projects or enhance existing codebases. It supports cloud and local LLMs including Claude 3.7 Sonnet, DeepSeek R1 & Chat V3, OpenAI o1, o3-mini & GPT-4o, and can connect to almost any LLM. Aider creates a map of your entire codebase for better context in larger projects and works with over 100 programming languages. It integrates with git to automatically commit changes with sensible messages, supports adding images and web pages for visual context, offers voice-to-code functionality, and automatically lints and tests code after changes. Aider can also be used within IDEs via comments and can copy/paste code to web chat interfaces.
Key Features
- Works with cloud and local LLMs (Claude, DeepSeek, OpenAI, local models)
- Maps entire codebase for context in large projects
- Supports 100+ programming languages
- Git integration with automatic commit messages and undo
- IDE integration via code comments
- Add images and web pages for visual context
- Voice-to-code feature for speaking changes
- Automatic linting and testing with fix capability
- Copy/paste interface for web chat LLMs
Use Cases
- Starting new projects from scratch
- Building on existing codebases
- Requesting new features via voice or text
- Writing test cases and bug fixes
- Refactoring and improving code quality
Pros & Cons
Pros
- Supports a wide range of LLMs including local models
- Automatic git commits with descriptive messages
- Voice-to-code enables hands-free development
- Can provide context from images and web pages
- Linter and test integration catches errors early
- Open source and free to use
Cons
- Requires API keys for cloud-based LLMs
- Initial setup may be complex for non-technical users
- Dependent on LLM availability and latency
- Limited to terminal-based workflow without native IDE plugin