AI coding agent project management / orchestration
CCPM is an agent skill system that turns ideas into PRDs, GitHub issues, and parallel coding agents via git worktrees, with full traceability.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose if you need a lightweight Rust blackboard to share context across many agent CLIs instead of a GitHub-Issues PM process.
🏄🏼♂️ The blackboard for coding agents - agentic development environment for claude code, codex, cursor, opencode, grok and more.
choose if you want a TypeScript teams-first orchestration layer specifically for Claude Code, without the PRD/issue workflow.
Teams-first Multi-agent orchestration for Claude Code
choose if you only need parallel git-worktree execution for several agents and want a minimal TypeScript CLI.
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree
choose if you want a Go/AGPL terminal manager for many agent CLIs with no spec-driven PM overhead.
Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.
choose if you want a Plan-Apply-Unify loop for Claude Code that emphasises quality gates over issue tracking.
Plan-Apply-Unify Loop — Structured AI-assisted development for Claude Code. Quality over speed-for-speed's-sake.
choose if you want self-correcting memory and 17 battle-tested skills with parallel worktrees, rather than a strict PRD/issue system.
Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.
choose if you want a TUI/Web manager to control agents from mobile and support many CLI agents.
Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI, Factory Droid Coding.
choose if you want a self-contained JavaScript harness with memory, 15 agents, and 33 skills rather than a GitHub-Issues PM skill.
Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack
choose if you need a session manager to switch between many coding agent CLIs, not a full PM workflow.
Coding Agent Session Manager for Claude Code / Gemini CLI / Codex CLI / Cursor Agent / Copilot CLI / Cline CLI / OpenCode / Kimi CLI
choose if you want a professional harness with TDD, persistent memory, and quality gates, in JavaScript.
How real engineers run Claude Code and Codex: spec-driven planning, enforced TDD, persistent memory, and quality enforcement on all levels. Make your agents production-ready.
choose if you want a single Go binary with zero dependencies and built-in quality gates/routing for spec-driven development.
Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16 languages, zero deps.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
choose if you prefer a minimal evidence-first development skill for your agents, and don't need the full issue/worktree management.
An old coder's strategy for the agent era: don't read the code — make it run the gauntlet. Evidence-first development skill for coding agents, inspired by Uncle Bob.
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
choose if you prefer a visual kanban dashboard with auto-merge rather than a skill you install into an agent harness.
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
choose if you want a desktop app to visually run and compare parallel agent sessions; note it hasn't been updated in 6 months.
(Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, compare approaches & manage AI-assisted development workflows in one desktop app.
choose if you want an IDE to run 100+ agents on your own subscriptions, not a skill-based PM.
Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
choose if you want a self-hosted kanban environment with PR review, but it runs as a separate web app.
AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.
choose if you want a dedicated IDE for AI coding agents instead of a lightweight skill.
The IDE built for AI coding agents.
These projects were analysed and named ccpm among their alternatives. The relationship is not symmetric — how ccpm rates them is a separate judgement, made when ccpm is analysed in its own right.
calls ccpm “Choose it if you prefer managing parallel agent execution through GitHub Issues and worktrees rather than a dedicated IDE.”
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.