Aider is a terminal-based AI pair programming tool that lets you edit code in your local git repository using natural language. You describe the change you want, and Aider proposes and applies edits to your files, then commits them with helpful messages. Built by Paul Gauthier, it aims to be the fastest way to get AI assistance integrated into a normal Git workflow — everything happens in your existing repository, so diffs, branches, and history all stay first-class.
Key Features
Git-Native Workflow: Automatically commits changes with descriptive messages; keeps diffs reviewable in your repo
Whole-Repo Context: Uses a repo map to understand your codebase, not just the current file
Terminal-First: Runs entirely in the command line alongside your editor — no separate GUI needed
Multiple Model Support: Works with a wide range of models, including local models and hosted APIs
Voice Input: Optional voice coding lets you dictate changes
Scripting & Integration: Expose a scriptable interface and hooks so it fits into existing build/test pipelines
Image Support: Include screenshots and images in your prompts for UI changes and visual fixes
Why Use It
Aider is ideal for developers who live in the terminal and want AI assistance that respects Git. Because it commits its own work, you always know exactly what changed and can revert or squash with standard Git commands. Its repo-wide context means suggestions reflect your actual architecture rather than a single file. If your workflow already centres on Git and a CLI, Aider integrates with almost zero disruption.
Use Cases
Refactoring: Ask it to rename symbols, split a module, or update call sites across the repo
Unit tests: Describe the behaviour and let it write and commit test cases
Dependency upgrades: Guide it through breaking API changes and fix compilation errors
Scripting jobs: Automate code edits in a pipeline using Aider’s scriptable interface
Platform
Linux, macOS, Windows (incl. Windows Subsystem for Linux)
Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports a wide range of LLM runners including Ollama and OpenAI-compatible APIs, with a built-in inference engine for Retrieval Augmented Generation (RAG). With over 146,000 GitHub stars, it has become the go-to interface for running local AI models […]