Aider
Open-source command-line AI coding partner that edits code directly in your local git repo. Bring your own API key, pay only for what you use.
Updated 2026-04-30
Overview
Aider is a command-line tool that lets you pair-program with LLMs directly in your terminal. Point it at a git repo, tell it what you want to change in plain English, and it edits your source files and commits the results. It's not a code completion plugin or an IDE — it's a conversation-driven coding partner that works alongside whatever editor you already use.
What sets Aider apart from GUI-based AI coding tools is its deep git integration. Every change Aider makes is automatically committed with a descriptive message, giving you a clean history and easy rollback. It builds a "repo map" using tree-sitter to understand your project's structure — classes, functions, imports — so it can make accurate edits across multiple files without losing context.
Aider supports a wide range of models including Claude Sonnet/Opus, GPT-4o, Gemini, DeepSeek, and local models via Ollama. Since it's BYOK (bring your own key), you pay only for the API calls you make. This makes it especially popular with developers who want maximum flexibility and transparency over costs, and who don't want to abandon their existing terminal-centric workflow for a new IDE.
What sets Aider apart
- Automatically git-commits every AI change with a descriptive message for a clean audit trail
- Builds a tree-sitter repo map to make accurate edits across multiple files
- Works with any LLM — Claude, GPT-4o, Gemini, DeepSeek, or local Ollama models
- Free, open-source, bring-your-own-API-key pricing with no turnkey subscription
Key features
Terminal-based
Runs entirely in the terminal with no GUI overhead. Works with tmux, SSH sessions, and remote dev environments. Integrates with your existing editor and shell workflow.
Git-native
Every AI-generated change is automatically committed with a descriptive message. Clean diffs, easy rollbacks, and full audit trail of what the AI changed and why.
Multi-model
Supports Claude, GPT-4o, Gemini, DeepSeek, Llama, and dozens more via OpenAI-compatible APIs or Ollama for local models. Switch models mid-session with /model.
Pricing
Free tier: The tool itself is completely free and open-source. You pay only for LLM API usage from your chosen provider.
| Plan | Price | What's included |
|---|---|---|
| Aider (tool) | Free | Open-source, install via pip, unlimited usage |
| LLM API costs | Pay-per-use | You pay your LLM provider directly — typically $0.01–$0.10 per coding request depending on model |
Open-source, install via pip, unlimited usage
You pay your LLM provider directly — typically $0.01–$0.10 per coding request depending on model
Pros & cons
Pros
- ✓Completely open-source with an active community and frequent updates
- ✓Automatic git commits give a clean audit trail and easy rollback for every AI change
- ✓Works with any LLM — swap between Claude, GPT, Gemini, or local models freely
- ✓No IDE lock-in: use it alongside Vim, Emacs, VS Code, or anything else
Cons
- ×Terminal-only interface has a steep learning curve for non-CLI users
- ×Requires your own API keys — no turnkey experience like Cursor or Copilot
- ×No inline code completion or real-time suggestions; it's conversation-driven only
- ×Large codebases can burn through API tokens quickly with repo-map context
How it compares
| Tool | Best for | Pricing | Score |
|---|---|---|---|
| Aider | Terminal-based developers who want an AI pair programmer that edits their local git repo directly, without adopting a new IDE. | Free (BYOK — pay your LLM provider) | 8.6/10 |
| Cursor vs Cursor → | Professional developers handling complex, multi-file refactors who want AI built into a familiar VS Code-based editor. | Freemium | 9.5/10 |
| GPT-5.5 vs GPT-5.5 → | Developers and teams needing a frontier reasoning model for agentic coding workflows and large-codebase context handling. | API: $5/$30 per 1M tokens (in/out). ChatGPT Plus $20/mo, Pro $200/mo | 9.4/10 |
| Windsurf vs Windsurf → | Developers who want an AI IDE that autonomously plans, codes, tests, and iterates across a project with minimal input. | Freemium | 9.1/10 |
Compare head-to-head
Related reading
GLM-5.2: Z.ai Open Model Tops Coding Benchmarks
Z.ai's GLM-5.2 open-weights model beats GPT-5.5 on long-horizon coding benchmarks at a fraction of the cost, per VentureBeat.
OpenAI Codex Security CLI: Setup and the Catch
OpenAI open-sourced the Codex Security CLI on July 29. What it scans, what to check before wiring it into CI, and who is grading whose homework.
Pacing the Frontier: 1,100 Lab Staff Sign On
A petition at pacingthefrontier.com drew 1,100+ signatures from OpenAI, Anthropic, Google and Meta staff. What it asks for, and what the count hides.
Ready to try Aider?
Head to the official site to start with Aider — pricing and plans are listed above.
Visit Aider