- Specs capture user intent and requirements
- Issues track agent tasks and implementation work
- Relationships model dependencies between work items
- Feedback enables agents to improve specs as they implement
Why sudocode?
Persistent Context
Context survives beyond chat sessions—specs and issues live in git
Multi-Agent Ready
Multiple agents work concurrently with automatic coordination
Git-Native
Everything in
.sudocode/ within your repo—you own your dataLearn Why sudocode Matters
Understand the problems sudocode solves and how it transforms AI-assisted development
Quick Start
Get up and running in minutes:Installation
Install the CLI, MCP server, or Claude Code plugin
Quick Start Guide
Create your first spec and issue in under 5 minutes
Learn the Core Concepts
Understand how sudocode organizes context:Specs
Capture user requirements and design decisions
Issues
Track agent tasks and implementation work
Relationships
Model dependencies and connections between work
Feedback
Enable bidirectional learning between agents and specs
Integration Guides
Connect sudocode to your AI agents and workflows:MCP Integration
Use sudocode with Claude Code and other MCP-compatible agents
CLI Reference
Master the command-line interface for all operations
API Reference
Build custom integrations with the REST API
Workflows
Learn spec-driven development and best practices
Key Features
- Dual representation: Human-readable markdown + machine-queryable JSONL
- Graph-based planning: Topological ordering finds ready work automatically
- Bidirectional linking: Obsidian-style
[[SPEC-001]]references with backlinks - Smart anchoring: Feedback tracks specific lines and relocates intelligently
- Distributed sync: Git handles distribution; AI handles merge conflicts
- Multiple interfaces: CLI, MCP server, REST API, and web UI
Community & Support
Philosophy: Context should be treated like code—version-controlled, collaboratively edited, and evolved alongside your implementation. sudocode makes this possible for AI-assisted development.

