Skip to main content
Codebuff is an open-source AI coding assistant that edits your codebase through natural language instructions. Instead of using one model for everything, it coordinates specialized agents that work together to understand your project and make precise changes. Codebuff beats Claude Code at 61% vs 53% on our evals across 175+ coding tasks over multiple open-source repos that simulate real-world tasks.

How it works

When you ask Codebuff to “add authentication to my API,” it might invoke:
1

File Picker Agent

Scans your codebase to understand the architecture and find relevant files
2

Planner Agent

Plans which files need changes and in what order
3

Editor Agent

Makes precise edits to your code
4

Reviewer Agent

Validates changes to ensure quality
This multi-agent approach gives you better context understanding, more accurate edits, and fewer errors compared to single-model tools.

Key features

Multi-agent architecture

Specialized agents work together to tackle complex coding tasks with better context understanding

Custom workflows

TypeScript generators let you mix AI generation with programmatic control

Any model on OpenRouter

Use Claude, GPT, Qwen, DeepSeek, or any model on OpenRouter - not locked to one provider

Reusable agents

Compose existing published agents from the Agent Store to accelerate development

Production SDK

Build Codebuff into your applications with custom tools and CI/CD integration

Open source

Apache 2.0 licensed - inspect, modify, and contribute to the codebase

Why choose Codebuff

Custom workflows: TypeScript generators let you mix AI generation with programmatic control. Agents can spawn subagents, branch on conditions, and run multi-step processes. Any model on OpenRouter: Unlike Claude Code which locks you into Anthropic’s models, Codebuff supports any model available on OpenRouter - from Claude and GPT to specialized models like Qwen, DeepSeek, and others. Switch models for different tasks or use the latest releases without waiting for platform updates. Reuse any published agent: Compose existing published agents to get a leg up. Codebuff agents are the new MCP! SDK: Build Codebuff into your applications. Create custom tools, integrate with CI/CD, or embed coding assistance into your products.

What you can do

Just tell Codebuff what you want and it handles the rest:
  • “Fix the SQL injection vulnerability in user registration”
  • “Add rate limiting to all API endpoints”
  • “Refactor the database connection code for better performance”
Codebuff will find the right files, make changes across your codebase, and run tests to make sure nothing breaks.

Get started

Quickstart

Get from zero to your first working example in 5 minutes

Installation

Install the CLI or SDK with detailed setup instructions

CLI Guide

Learn how to use Codebuff from the command line

Agent Development

Build custom agents with specialized workflows

Community and support

Documentation

Comprehensive guides and API references

Discord

Join our community for help and discussions

GitHub Issues

Report bugs and request features

Contributing

Learn how to contribute to Codebuff

Build docs developers (and LLMs) love