QM is a multiplayer agent harness that lets each employee and room work with personal-assistant agents in Slack and on the web. It is designed to run in your own cloud with your own models and keys.
Project overview
It addresses the coordination problem that emerges when personal-assistant agents are used across a whole company, giving every person and room isolated workspaces while keeping a single agent identity across Slack and the web.
Project type
AI Agent
Use cases
Automation
Deployment
Refer to project documentation
License
MIT
Best for
Organizations that want to run personal-assistant agents for many employees at once, self-hosted in their own cloud with their own models and keys.
Developers comfortable setting up an agent application via CLI.
Key capabilities
The same agent identity and configuration carries between Slack and the web app, with personal and shared scopes.
Each person and room gets its own scoped memory, files, keychain view, permissions, crons, web apps, and durable sandbox where installed tools stay installed.
Limitations and risks
Without DATABASE_URL and SESSION_STORE=postgres, sessions live in process memory and vanish on restart.
Getting started
Run npm exec --yes --package=@yc-software/qm@latest -- qm init . --org <slug> --target <fly-or-aws>, then run npm install, and follow the deployment skill for infrastructure, deployment, and live verification. Setup difficulty is medium.
Evidence and sources
GitHub project description: Multiplayer agent harness for work.
README: Each person and each room has its own scoped memory, files, keychain view, permissions, crons, web apps, and durable sandbox.
README: - **Slack and web.** The same identity and configuration carries between Slack and the web app.
README: Work in an existing repository: run tests, open PRs, monitor CI, check system logs
README: For durability, set `DATABASE_URL` and `SESSION_STORE=postgres` — without it, sessions live in process memory and vanish on restart.