About Aider
Overview
Aider is an AI pair programming tool that runs in your terminal. It pairs you with LLMs to start a new project or build on your existing codebase. Aider works best with Claude 3.7 Sonnet, DeepSeek R1 and Chat V3, and OpenAI o1, o3-mini, and GPT-4o, but it can connect to almost any LLM, including local models.
Aider builds a map of your entire codebase, which helps it work well in larger projects, and it supports more than 100 programming languages, including Python, JavaScript, Rust, Ruby, Go, C++, PHP, HTML, and CSS. It automatically commits changes with sensible commit messages, runs inside your favorite IDE or editor, accepts images and web pages for visual context, and lets you speak to code with voice-to-code.
Key Benefits
- Connects to cloud LLMs like Claude 3.7 Sonnet, DeepSeek, and OpenAI o1, plus local models.
- Maps the entire codebase so it works well in larger projects.
- Supports 100+ programming languages, including Python, JavaScript, Rust, and Go.
- Automatically commits changes with sensible commit messages.
- Adds images and web pages for visual context, screenshots, and reference docs.
- Lints and tests code after every change and fixes detected problems.
How It Works
Install aider with python -m pip install aider-install, then change directory into your project. Launch aider with a model and API key, such as aider --model sonnet --api-key anthropic=<key> or aider --model deepseek --api-key deepseek=<key>. Describe the changes you want, and aider reads your codebase, applies the edits, lints and tests them, and commits the results.
Use Cases
- Developers starting a new project use aider to pair with an LLM from the terminal.
- Teams building on an existing codebase request new features and bug fixes through chat.
- Developers in large repositories rely on the codebase map to keep edits on target.
- Coders in their IDE add comments to code and let aider implement the changes.
- Users speak requests for new features, test cases, or bug fixes with voice-to-code.
Why Choose This Product
Aider pairs cloud and local LLMs with an automatic codebase map, git integration, and built-in linting and testing, all from the terminal or your editor. The project reports 44K GitHub stars, 6.8M installs, and 15B tokens processed per week.
Aider Pros & Cons
- Connects to Claude, DeepSeek, OpenAI, and local LLMs
- Maps the entire codebase for larger projects
- Auto-commits git changes with sensible messages
- Voice-to-code plus linting and testing built in
- 44K GitHub stars and 6.8M installs
- Not optimized for quick performance in very large repos
Key Features
Codebase map
Aider builds a map of your entire codebase, which helps it work well in larger projects.
Cloud and local LLMs
Aider works best with Claude 3.7 Sonnet, DeepSeek R1 and Chat V3, and OpenAI o1, o3-mini, and GPT-4o, and connects to almost any LLM, including local models.
100+ languages
Aider works with most popular programming languages, including Python, JavaScript, Rust, Ruby, Go, C++, PHP, HTML, and CSS.
Git integration
Aider automatically commits changes with sensible commit messages so you can use familiar git tools to diff, manage, and undo AI changes.
IDE support
Use aider from within your favorite IDE or editor by adding comments to your code for aider to implement.
Images and web pages
Add images and web pages to the chat to provide visual context, screenshots, and reference docs.
Voice-to-code
Speak requests for new features, test cases, or bug fixes and let aider implement the changes.
Linting and testing
Aider automatically lints and tests your code every time it makes changes and can fix problems its linters and test suites detect.
Web chat copy/paste
Aider can work with an LLM through its web chat interface, handling copy/paste of code back and forth with a browser.