Code Assistant Apache-2.0

Aider

Terminal-based AI pair programming tool. Edit code in your repo through conversation with automatic git commits, multi-file editing, and broad LLM support.

Platforms: windowsmacoslinux

Aider is a terminal-based AI pair programming tool that lets you edit code in your local git repository through natural language conversation. It reads your codebase, applies multi-file edits based on your instructions, and automatically creates descriptive git commits for each change. For developers who prefer the command line and want an AI collaborator that directly modifies their code with proper version control, Aider is the most capable terminal-based coding assistant available.

Key Features

Direct code editing. Unlike chat-based assistants that show you code to copy-paste, Aider edits your files directly. Describe what you want changed, and Aider modifies the relevant files in your working directory. Review the changes with git diff before continuing.

Automatic git integration. Every change Aider makes is automatically committed to git with a descriptive commit message. This creates a clean history of AI-assisted changes that can be reviewed, reverted, or cherry-picked individually. Your work is never lost.

Multi-file awareness. Aider can add multiple files to the chat context and make coordinated changes across them. Refactor a function and update all its callers, add a feature across model, controller, and test files, or restructure entire modules in a single conversation.

Repository map. Aider builds a map of your entire repository structure and can reference code from files not explicitly added to the conversation. This gives it awareness of your project’s architecture, APIs, and conventions without loading every file into context.

Broad LLM support. Aider works with OpenAI, Anthropic, local Ollama models, and any OpenAI-compatible API. It includes model-specific optimizations and benchmarks showing which models perform best for code editing tasks. Use local models for privacy or cloud models for quality.

Linting and testing integration. Aider can run linters and test suites after making changes, automatically fixing issues that the edits introduce. This creates a tighter feedback loop where the AI iterates until the code passes quality checks.

When to Use Aider

Choose Aider when you want AI coding assistance in the terminal that directly modifies your files with proper git hygiene. It excels for developers who live in the terminal, need multi-file refactoring, want automatic version control of AI changes, and prefer conversation over form-based IDE panels.

Ecosystem Role

Aider occupies a unique position as the terminal-native code editor. While Continue and Tabby integrate into IDEs, Aider works independently of any editor. It uses external LLM backends (Ollama for local, cloud APIs for remote) and focuses on the developer workflow of writing and editing code through conversation. For IDE integration, Continue is the alternative. For team deployment, Tabby adds administration features.