This page may contain affiliate links. We may earn a commission if you purchase through our links, at no extra cost to you. Learn more.

Aider — Open-source AI pair programming in the terminal with git-native workflows

Aider

Open-source AI pair programming in the terminal with git-native workflows

4.5/5

What is Aider?

Aider is an open-source AI pair programming tool that runs in the terminal, enabling developers to collaborate with LLMs to edit code in their local git repositories. It stands out for its git-native approach: every AI-generated change is automatically committed with a descriptive message, creating a clean history that makes it easy to review, accept, or revert AI contributions.

The tool supports a wide range of LLM providers including OpenAI, Anthropic, Google, and local models via Ollama. Aider's architecture-aware editing sends only relevant context to the model, keeping costs manageable while maintaining accuracy. It can work with multiple files simultaneously, understanding relationships between components to make coherent cross-file changes.

Aider has consistently ranked at the top of independent coding benchmarks, demonstrating strong performance in code generation, editing, and refactoring tasks. Its open-source nature means full transparency into how it works, an active community contributing improvements, and the flexibility to customize its behavior for specific workflows and team needs.

Key Features

  • Open-source terminal-based AI pair programmer
  • Automatic git commits for every AI change
  • Multi-model support (OpenAI, Anthropic, local)
  • Multi-file editing with architecture awareness
  • Bring-your-own-key model (no markup)
  • Repository map for intelligent context selection
  • Voice coding via speech-to-text
  • Linting and testing integration
  • Image and URL context support
  • Active open-source community

Pros & Cons

Pros

  • Fully open-source with transparent operation
  • Git-native workflow with automatic commits
  • Top performance on independent coding benchmarks
  • Bring-your-own-key means no markup on API costs

Cons

  • Terminal-only interface is not for everyone
  • Requires managing your own API keys and costs
  • No visual diff preview before applying changes
  • Learning curve for optimal prompting techniques

Pricing

Model: bring-your-key

PlanPriceKey Limits
Free (OSS)$0Full features, bring your own API keys, community support
API CostsVariesPay your LLM provider directly (OpenAI, Anthropic, etc.)
Local Models$0Use free local models via Ollama, no API costs

Frequently Asked Questions

undefined
undefined
undefined
undefined
undefined
undefined
undefined
undefined