Inside QM: We read Y Combinator’s company-wide agent runtime

QM gives each employee and shared room a durable computer, memory, credentials and background jobs, then routes four different coding-agent harnesses through one policy core. The open release is ambitious, legible and unusually candid about where its security model breaks down.

By · Published

Primary source: GitHub

Why it matters

QM turns YC's experience operating more than 50 internal agents into a self-hostable control plane, making permissions, persistent workspaces and fleet administration the core infrastructure problem.

AI agent runtime architecture and its security vulnerabilities (Photocopied zine page: high-contrast xerox grain, rough cut-and-paste layout, distressed and degraded texture from multiple generations of copying.)

Code reviewed: yc-software/qm at commit 7f2c916, the source revision recorded in npm package @yc-software/[email protected]

Two days after Y Combinator published QM, the project had already drawn 6,600 GitHub stars, 700 forks, 68 pull requests and 14 open issues. That attention makes sense. QM is one of the first open-source attempts by a prominent organization to turn the local coding-agent pattern into shared company infrastructure.…

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Reader comments

Conversation for this story loads after sign-in.