ccpm  by automazeio

AI project management for parallel agent execution

Created 1 month ago
4,682 stars

Top 10.6% on SourcePulse

GitHubView on GitHub
Project Summary

Project Summary

Automazeio/ccpm is a project management system designed for AI-assisted software development, specifically targeting teams using Claude Code. It addresses common issues like context loss, parallel work conflicts, and lack of traceability by leveraging GitHub Issues and Git worktrees. The system enables multiple AI agents to work in parallel on distinct tasks, all while maintaining a clear audit trail from product requirements to production code, thereby improving team collaboration and development velocity.

How It Works

The system operates on a spec-driven development principle, ensuring every line of code traces back to a specification. It uses a five-phase discipline: Brainstorm, Document, Plan, Execute, and Track. The core innovation lies in its parallel execution model, where a single GitHub issue can be broken down into multiple, concurrently running AI agents, each handling a specific sub-task within its own isolated context. This approach optimizes context preservation by preventing implementation details from polluting the main conversation thread, allowing the primary thread to remain strategic. GitHub Issues serve as the single source of truth, facilitating seamless human-AI handoffs and providing transparency for team members and managers.

Quick Start & Requirements

  • Installation: Clone the repository into your project directory and run /pm:init to install dependencies (including GitHub CLI and gh-sub-issue extension if needed), authenticate with GitHub, and set up project structure.
  • Prerequisites: GitHub CLI, Git.
  • Setup Time: Approximately 2 minutes for initialization.
  • Documentation: See It In Action (60 seconds), Example Flow, Get Started Now.

Highlighted Details

  • Context Preservation: Each epic maintains its own context, with agents reading from and updating local files before syncing.
  • Parallel Execution: Tasks can be marked for parallel execution, enabling conflict-free concurrent development by multiple agents.
  • GitHub Native: Integrates with existing GitHub workflows, using issues as the source of truth and comments for history, without relying on the GitHub Projects API.
  • Full Traceability: Provides an end-to-end audit trail from PRD to code commits (PRD → Epic → Task → Issue → Code → Commit).
  • Proven Results: Claims include 89% less context switching time, 5-8 parallel tasks vs. 1, 75% bug reduction, and up to 3x faster feature delivery.

Maintenance & Community

  • Developed by Automaze.
  • Follow @aroussi on X for updates.
  • Star the repository to show support.

Licensing & Compatibility

  • The repository's license is not explicitly stated in the provided README. Compatibility for commercial use or closed-source linking would require clarification on the license.

Limitations & Caveats

  • The README does not specify the project's license, which is crucial for determining commercial use and compatibility.
  • While the system aims for seamless integration, the effectiveness of parallel agent execution and context management may depend on the complexity of the tasks and the capabilities of the AI model used.
Health Check
Last Commit

3 weeks ago

Responsiveness

Inactive

Pull Requests (30d)
15
Issues (30d)
588
Star History
4,729 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.