Aider

What is Aider?

Aider is an open-source, terminal-based AI pair programmer, released under the Apache-2.0 licence. You run it in your shell inside a git repository and describe changes in natural language; Aider edits the relevant files and — distinctively — commits each change to git with a sensible message, so every AI edit is a reviewable, revertible commit. It is bring-your-own-key and model-agnostic, working with Anthropic, OpenAI, DeepSeek, local and effectively any LLM. Free and widely adopted (47,000+ GitHub stars and 6.8 million installs), it is a favourite of developers who live in the terminal and want AI edits kept under version control.

What does Aider do?

You launch Aider in a terminal, point it at files (or let it use its repository map to find them) and ask for a change; it sends the relevant code plus a compact map of the whole codebase to your chosen model, applies the edits, and commits the result to git with a descriptive message. Because every change is its own commit, you can review diffs, undo cleanly, or let Aider run tests and linters and automatically fix what breaks. It supports 100+ languages, can accept images and web pages as context, offers voice-to-code, and has a watch mode that lets you drive it from comments in your normal IDE. Its clipboard/web-chat mode even lets you pair with browser-based models. A hallmark of the project is its public code-editing and “polyglot” leaderboards, which benchmark how well different models perform Aider’s edit format — a widely cited, independent signal on model coding ability. An optional “architect” mode splits the work across two models — a strong reasoning model proposes the solution, then a separate “editor” model turns it into the actual file edits — which trades an extra API call for noticeably better results on hard problems and models that reason well but edit poorly. There is also an experimental --browser web UI for people who want a local browser tab instead of a raw terminal, though the terminal remains the primary, most complete interface. Everything runs locally under your control; you supply the API key (or a local model) and pay the provider directly, so the tool itself stays free.

Key features

• Git-native commits: Every AI edit lands as a git commit with a sensible message, so changes are reviewable and revertible by default.
• Repository map: Sends a compact Tree-sitter map of the whole codebase so the model has context on large projects without dumping every file.
• Architect/editor mode: Splits a hard task across two models — one proposes the solution, a second turns it into precise file edits — for better results at the cost of an extra API call.
• Model-agnostic, BYO key: Works with Claude, GPT, DeepSeek, local and nearly any LLM; you supply the key and pay the provider directly.
• Auto lint & test fixes: Can run your linters and tests after an edit and automatically fix what it broke.
• Public model leaderboards: Maintains widely-cited code-editing and polyglot benchmarks of how well models perform its edit format.

What are Aider's use cases?

• Terminal-first development: A developer who lives in the shell makes AI edits without leaving the terminal or their existing editor.
• Version-controlled AI edits: A team keeps every AI change as a clean, revertible git commit for easy review.
• Model evaluation: An engineer uses Aider’s edit format and leaderboard to compare how models actually perform on code edits.

What does Aider integrate with?

• Git (native commits)
• Model providers — Anthropic, OpenAI, DeepSeek, local/Ollama
• IDEs via watch mode (edit-from-comments)
• Linters & test runners

Why use Aider?

• Free and open-source (Apache-2.0), with no subscription — you pay only your model provider.
• Git-native: every edit is a reviewable, revertible commit, which is safer than in-place AI edits.
• Model-agnostic, including cheap and local models, with a repo map that scales to large codebases.

Pros & cons

Aider pricing

• Open source (BYO key)Free

See current pricing on aider.chat ↗Compare Aider alternatives →

Aider review

Aider is the definitive terminal AI pair programmer: open-source under Apache-2.0, model-agnostic, and built around a git-native workflow where every AI edit becomes a reviewable, revertible commit. That commit discipline plus its repository map and auto lint/test fixing make it one of the safest ways to let a model touch a real codebase, and being bring-your-own-key keeps it free and flexible — route work to Claude, GPT, DeepSeek or a local model as you like. Its well-known code-editing leaderboards are a genuinely useful, oft-cited signal on model ability. The trade-offs are that it is terminal-only with a steeper on-ramp than a GUI tool, you pay your provider per token, and it is an interactive pair programmer rather than a fire-and-forget agent. Pick Aider if you live in the terminal and want free, auditable, model-agnostic AI edits under git; skip it if you want a graphical editor or a fully autonomous cloud agent.

The terminal purist’s choice — free, model-agnostic, and the git-commit discipline makes AI edits genuinely safe to review.

Frequently asked questions