Why it is worth attention

It solves the complexity of scaling a single personal assistant to a whole company by providing per-user and per-channel scopes, while remaining model-agnostic and open-source, avoiding vendor lock-in and allowing startups to own their deployment.

Who it is for

Startups wanting to give each employee a personalized AI agent
Small teams needing shared agent collaboration in Slack and web
Developers building internal tools and custom skills for their organization
Organizations seeking a self-hosted, private AI agent infrastructure

Use cases

Search and retrieve information across internal notes, email, documents, and databases
Build, publish, and maintain internal web apps with up-to-date data
Automate code repository tasks: run tests, open PRs, monitor CI, check logs
Track projects in shared Slack channels with periodic updates and follow-ups

Strengths

Personal and shared scopes allow customization and collaboration without interference
Consistent identity and configuration across Slack and web UI
Open-source and model-agnostic, supporting Pi, OpenCode, Codex, and Claude Code
Configurable security postures (strict, auto, dangerous) with predeclared command policies

Considerations

Requires a PostgreSQL database for persistence, adding operational overhead
Deployment involves setting up infrastructure in the operator's own cloud account with no built-in CI
The private fork approach for customization requires careful handling to avoid visibility and merge issues

README quick start

qm

A multiplayer agent harness for work. In Slack and on the web.

What is QM?

Most agents are designed like personal assistants. You can make one work for a whole company, but it quickly gets complex. QM is designed for startups. Employees each get their own isolated workspace and work independently without affecting each other, and they can also collaborate with the agent in channels, group messages, and projects.

Each person and each room has its own scoped memory, files, keychain view, permissions, crons, web apps, and durable sandbox.

It's built with open source in mind. Pick your own harness and model and switch between them — Pi, OpenCode, Codex, and Claude Code all drive the same core, so a deployment isn't tied to any single vendor.

Features

Personal and shared scopes. People customize the agent to be theirs, and still work with it collaboratively in Slack channels and projects.
Slack and web. The same identity and configuration carries between Slack and the web app.
Admin control. Set org-level configuration, a security posture, and which harnesses and models are available.
Web apps. Spin up custom internal apps and publish them to the right people.
Shared skills. Skills are scope-owned and shareable by grant, with admin-gated promotion to the whole org and skill packs imported from git repositories.
Background work. Crons and watches run work while nobody's watching.

What you can do with it

Search internal notes, email, documents, databases, and the web together
Retrieve information from your company brain
Build internal apps, publish them to the right people, and keep their data current
Learn your writing voice from past sends, then triage your inbox on a schedule — labels and reply drafts included
Work in an existing repository: run tests, open PRs, monitor CI, check system logs
Track a project in a shared channel and post updates and follow-ups

Architecture

flowchart LR
  DB[("Postgressessions · memory · queue")]

  subgraph CORE["Headless core"]
    API["API · identity · policy · scheduler"]
    LOOP["Agent loop(Pi, OpenCode, Claude Code)"]
    API  LOOP
  end

  SBX["Per-scope sandboxfiles · tools · logged-in services"]

  DB  API
  LOOP  SBX

Every turn runs through a central core, which can use a variety of models and harnesses to generate t

Description

Multiplayer agent harness for work

Related repositories

Similar projects matched by category, topics, and programming language.

Jakubantalik

Featured

thinking-orbs

A React component library that renders six hand-tuned animated thought orb loading indicators on a plain 2D canvas, with two purpose-tuned sizes and automatic theme detection for AI and agent UIs.

AI & Machine LearningAI Agents

1,191

makecindy

Featured

cindy

Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

AI & Machine LearningLarge Language Models

958

mereyabdenbekuly-ctrl

Featured

clodex-ide

Clodex is an open-source, local-first agentic IDE that combines persistent AI tasks, code, terminal, browser, Git, models, memory, and governed execution in one Electron workspace, currently in technical preview.

AI & Machine LearningAI Agents

859