Skip to main content

Agentic Project Management (APM)

A spec-driven multi-agent framework for AI-assisted software engineering.

APM is an open-source framework for managing ambitious software projects with AI assistants - Claude Code, Cursor, GitHub Copilot, Antigravity, OpenCode, and Codex. Instead of working in a single, increasingly long conversation, APM structures your work into a coordinated system where different agents handle planning, coordination, and execution, and their messages pass through you.

The Problem​

A coding agent is an LLM working in a loop with tools. LLMs keep no state between calls: the agent resends the whole conversation for each step of a task. On long tasks, LLMs suffer from two problems:

  • Context decay - The longer the conversation and the more context accumulates, the less reliably the LLM recalls earlier decisions and instructions, and the less consistently it reasons about them.
  • Context pressure - Every call costs more than the last and brings the conversation closer to the context window's limit, where the platform must cut or summarise it, losing earlier detail.

How APM Works​

APM counters each problem, and keeps you in charge throughout.

  • Planning documents, against decay - APM is spec-driven. Before any code is written, a Planner works with you to record the project's intent, requirements, and constraints in three planning documents: the Spec (what to build), the Plan (how the work is divided), and the Rules (how the work is carried out). Agents work from these documents instead of relying only on what their long conversation holds.
  • Separate agents, against pressure - APM is a multi-agent system where a Manager hands out the work and Workers carry it out, each in its own conversation with only the context its work needs. Splitting the work this way keeps each conversation's context small and focused on its own job.
  • Coordination through you - The Planner, the Manager, and the Workers communicate only through you, by design. When one writes a message for another, it informs you, and you deliver it by running a command. Each exchange is a chance to review the work behind it and ask for changes before it moves on. How the work is divided and assigned sets how often exchanges pass through you. We call this productive friction. These pauses are deliberate: they aim to keep your understanding of the software you are building, and to let you catch mistakes before they spread through the codebase.

What distinguishes this from subagent-based approaches: the agents doing implementation work are not restarted fresh on each task. They accumulate working context across assignments, building familiarity with their domain as the project progresses. When context fills, a Handoff transfers that working knowledge to a fresh instance rather than discarding it. Any APM agent may delegate heavy work to its own subagents.

The APM workflow: in the Planning Phase you and the Planner write the Spec, the Plan, and the Rules; in the Implementation Phase the Manager hands out assignments and Workers report back through you, with the session's state in shared files.The APM workflow: in the Planning Phase you and the Planner write the Spec, the Plan, and the Rules; in the Implementation Phase the Manager hands out assignments and Workers report back through you, with the session's state in shared files.
The APM workflow. In the Planning Phase, on the left, you and the Planner turn your goals into planning documents; in the Implementation Phase, on the right, the Manager and Workers implement them together.

Throughout implementation, the Manager checks the work against the planning documents and Workers follow the Rules, under your supervision. Shared files outside any conversation hold the session's state and history. When a session ends, you can archive it, and later Planners can build on the archive.

Installation​

APM is installed via the agentic-pm CLI, which scaffolds the commands, guides, and skills that APM agents use into your project workspace. To get started, see Getting Started.

If you want your AI assistant to explain APM concepts or help with migration from an older version, the apm-assist skill can be installed into any project and answers questions by reading the live documentation.

Contributing​

APM is open source and welcomes contributions. Report bugs or request features via GitHub Issues, or submit improvements via Pull Requests.

For contribution guidelines, see CONTRIBUTING.md.

Reading Order​

Start using APM - Getting Started walks you through installation and your first session end to end. There is also a Quick Reference with every command and workflow in one place, to keep at hand.

Understand the architecture - Three docs build on each other: Agent Roles covers the three roles, Agent Orchestration covers how they coordinate, and Workflow Overview walks through every procedure.

Go deeper - Prompt Engineering explains how APM's files are designed. Context Engineering explains why each agent sees what it sees.

Look things up - CLI Guide for commands and options, Troubleshooting for common issues, Customisation for custom repositories, Security for the trust model, and Tips and Tricks for model selection and workflow efficiency.