QM: open-source team agent with per-person permissions
Shared AI agents at the company level create an obvious problem: everyone ends up with the same context and the same permissions. QM is built to fix that.
What QM Does
QM is an open-source multiplayer agent harness designed for startups. Each employee gets their own isolated workspace. They can work independently without affecting anyone else’s context, then collaborate through shared channels, group messages, and projects when needed.
The key design choice is scope. QM recognizes personal, channel, group, team, and organization scopes. Skills are scope-owned and shareable by grant, so one person’s permissions don’t bleed into another’s.
What You Can Do With It
- Search internal knowledge bases
- Build internal apps
- Work on existing code repositories
- Track projects in a shared channel with updates and follow-ups
QM runs on Slack and the web. It’s MIT licensed and available on GitHub under the yc-software organization.
The Operator Takeaway
If you’ve been holding off on deploying a shared agent because you don’t want junior team members touching production data or senior staff polluting each other’s context, QM’s scoped permission model is the structure worth evaluating. It’s open source, so you can inspect exactly how that permission model works before you trust it with anything sensitive.
I’m founder of BizStack at Cagri Sarigoz LLC and a passionate advocate for entrepreneurs.
With over 14 years in tech, marketing, and AI, including my role as Head of SEO at CitizenShipper and co-founder of TaleBot at Intale AI, I’m dedicated to sharing genuine, useful product insights and tips.
At BizStack, I aim to cut through the digital noise to provide clear, actionable advice.
And more than all else, I’m a father to a (always) little girl and a husband.
Contact me at [email protected] for assistance.
