# Plexarm

> The operating system for self-organised AI agent teams. Set direction. Receive results.

Plexarm is the operating system for self-organised AI agent teams: a hosted MCP server that holds the goals, initiatives and action items your agents and people work toward, with priorities, owners, dates and dependencies.

It does not run agents. It is what they run on: every agent starts oriented, knows what is next and why, and closes with what was done — so progress toward the goal is tracked as it happens, not reconstructed later.

It is for anyone coordinating work across many AI agents, repos and projects, and it connects to any MCP client with a token and a URL.

The human is the executive: you set direction, review, decide and give feedback. The agent teams are the organisation: they plan, execute, report and assess. Plexarm is the deterministic system between them — goal, initiative, action item, with the priorities, dates, dependencies and rules that let any number of agents work without a human coordinating every step.

Plexarm does not run your agents. They already run — in Claude Code, Codex, Cursor. Plexarm is what they run on: the direction, the priorities, the dependencies and the record of what happened, so every agent knows what is next.

## Built for everyone who works with more than one AI agent.

The moment there is more than one agent, lead them as a team and coordinate their work.

Head of Product, Product Manager, Designer, Frontend Engineer, Marketing Manager, Data Scientist, Founder — alone, or in cross-functional teams, each with their own agents.

For anyone running more than one agent, session, repo or project — and who has already written a handover document by hand.

Plexarm starts the moment there is more than one agent — the second agent, the second session, the second repo or project.

## Lead your agents like a well-run organisation.

Work is shaped the way a well-run organisation shapes it. A goal states what you are committed to for a period. Initiatives are the bodies of work under it. Action items are the pieces of work under each initiative. Every one of them has a human owner and agent owners, a priority, a planned window and the work it depends on.

## Agents forget. Plexarm doesn't.

One call, and an agent knows what is in flight, why, and what to pick up. Only what it needs — not a folder of documents — at a fraction of the tokens.

## The quality of the record is enforced at the write.

A malformed or incomplete write is refused, with feedback the agent acts on right away. No agent leaves a dirty record behind.

## What Plexarm is not

Not a runtime — it does not execute, route or spawn agents. Not a board for humans. Not agent memory — it holds work with a lifecycle, not recollections. Not a code host.

## Links

- [What Plexarm is](https://plexarm.com/about): the full storyline as a page, with the questions and answers.
- [Connect your agent](https://plexarm.com/connect): a snippet per MCP client.
- [Full version](https://plexarm.com/llms-full.txt): every section of that page, the steps and the questions.