QM

What is QM?

QM is an open-source agent harness built so a whole team can share one AI agent instead of each person running a personal assistant. Every employee gets an isolated workspace, and people can also work with the agent together in shared Slack channels, group chats and projects. Every individual and every shared room gets its own scoped memory, files, keychain view, permissions, scheduled jobs, web apps and durable sandbox. The same identity and configuration carry between Slack and the web app. Admins set organization-wide configuration, a security posture of strict, auto or dangerous, and choose which harnesses and models are allowed, with Pi and Claude Code able to drive the same core. You deploy it into your own cloud account with your own models and keys, using a CLI that validates and deploys a deployment directory. QM is released under the MIT License, so there is no license fee, though you pay for hosting and model usage yourself.

Use cases

• Share one agent across a startup team
• Search notes, email, documents and the web together
• Build and publish internal web apps
• Triage an inbox on a schedule with reply drafts
• Run tests and open pull requests in a repository
• Track a project in a shared Slack channel

Who it's for

• Startup teams
• Engineering leads
• Platform engineers
• Operations teams

Why use QM

• One deployment serves a whole company while keeping each person's memory and files separate.
• Running in your own cloud with your own keys avoids tying the agent to one vendor.
• Admins choose the security posture and which models are available, and narrower scopes can only tighten it.
• The MIT license and a source-fork route let you modify core behavior if the defaults do not fit.

QM features

• Personal and shared scopes for memory, files and permissions
• Slack and web interfaces that share one identity
• Durable per-scope sandbox where installed tools persist
• Admin control over security posture, sharing and available models
• Choice of harness, including Pi and Claude Code
• Shared skills with admin-gated promotion and skill packs from git
• Crons, watches and inbound webhooks for background work
• Internal web apps published to selected people
• Optional content screening in off, observe or enforce mode
• Postgres storage for sessions, memory and queue

QM integrations

• Slack
• Claude Code
• Pi
• Postgres
• GitHub

How to get started with QM

1. Ask your coding agent to deploy the repository, or run the qm init command to create a deployment repository.
2. Follow the generated deployment guide to set up infrastructure, web sign-in and connector credentials.
3. Optionally enable Slack access, then deploy and verify the live instance.
4. Choose a harness and models, set the security and sharing posture, and invite people.
5. Each person works in their own scope, and the team collaborates with the agent in channels and projects.

QM limitations

• You deploy and run it yourself in your own cloud account
• You supply model access and credentials
• Sessions live in process memory unless Postgres is configured
• Contributions are accepted as written descriptions rather than code

QM pricing

QM is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

QM alternatives

The main QM alternatives listed on Debuly are Claude Code, Glean, Lindy, Agent Barn, Agent Swarm and Context. The table compares pricing and platforms; order is A–Z.

1. 

   Agent Barn

   Open-source control plane for running AI agents in Slack, Teams and Telegram, with templates, skills, cost tracking and self-hosting.

   Automation and agentsDeveloper platformsProductivity
   Open sourceVisit Agent Barn (official site)
2. 

   Agent Swarm

   Self-hosted, MIT-licensed system where a lead agent hands work to Docker-isolated Claude Code, Codex and other coding workers.

   Automation and agentsCodingDeveloper platforms
   Open sourceVisit Agent Swarm (official site)
3. 

   Claude Code

   Anthropic's coding agent that fixes bugs, writes tests and runs migrations from your terminal, IDE, desktop app, web or Slack.

   CodingAutomation and agentsDeveloper platforms
   PaidVisit Claude Code (official site)
4. 

   Context

   Workspace and runtime for AI agents that run in your own cloud, with shared files, chat, evals and per-agent identity.

   Automation and agentsDeveloper platformsProductivity
   FreemiumVisit Context (official site)
5. 

   Glean

   Enterprise AI platform that searches company apps, answers questions with permissions respected, and runs agents on your own data.

   ProductivityResearch and searchAutomation and agents
   Contact salesVisit Glean (official site)
6. 

   Lindy

   AI teammate that handles email, scheduling, meetings and recurring routines across 1,500+ apps, with credit-based pricing.

   Automation and agentsProductivityChat assistants
   Free trialVisit Lindy (official site)

QM FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from avatars.githubusercontent.com · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.