Verified project record
yc-software/qm
qm is a self-hosted multiplayer agent harness that gives employees isolated workspaces while supporting collaboration across channels, group messages, and projects. It combines scoped durable resources with configurable harness and model choices, background work, search, repository operations, and internal web apps.
Project overview
qm deserves attention for combining person- and room-scoped agent resources with shared organizational collaboration, while allowing deployments to choose their harnesses and models instead of tying the system to one vendor.
- Project type
- Workflow
- Use cases
- Documents & Office · Search & Research · Automation
- Deployment
- Refer to project documentation
- License
- MIT
Best for
- Organizations seeking a shared agent system with independent employee workspaces and collaboration across channels, messages, and projects.
- Teams that need memory, files, permissions, scheduled work, web apps, and sandboxes separated by person or room scope.
- Operators prepared to manage a self-hosted deployment, organization configuration, connector credentials, and cloud infrastructure.
Key capabilities
- Provides each employee with an independent workspace so that one employee's work does not affect another's workspace.
- Supports collaboration with the agent in channels, group messages, and projects while maintaining separate person and room scopes.
- Maintains per-person and per-room memory, files, keychain views, permissions, crons, web apps, and durable sandboxes.
- Allows administrators to set organization-level configuration and security posture and control which harnesses and models are available.
- Supports creating custom internal apps and publishing them to selected people.
- Provides scope-owned skills that can be shared through grants, supports administrator-gated organization-wide promotion, and imports skill packs from Git repositories.
- Runs scheduled or event-driven work through crons, watches, and inbound webhooks.
- Supports combined searches across internal notes, email, documents, databases, and the web.
Limitations and risks
- The repository does not provide a production deployment workflow, so adopters need to account for that gap when planning production operation.
- The Dangerous security posture performs no content screening and disables pauses between tool calls. Teams considering this posture should review whether those settings are appropriate for their deployment.
Getting started
- Run `npm exec --yes --package=@yc-software/qm@latest -- qm init . --org <slug> --target <fly-or-aws>`, then run `npm install`.
- Proceed through infrastructure setup, web sign-in, connector credentials, optional Slack access, deployment, and live verification. The documented setup difficulty is medium because this path spans those configuration and deployment stages.
Evidence and sources
- GitHub project description: Multiplayer agent harness for work.
- README: Tell your coding agent of choice `Let's deploy https://github.com/yc-software/qm`. From here, it should follow the deployment guide in this repo.
- README: 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 ow…
- README: - **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 i…
- Release: v0.1.5
AI Search
Find projects, verify facts, compare options, or turn a complex need into an actionable plan
Try a searchA click only fills the search box; you stay in control
Project Details
0