H
pending
Y Combinator Open-Sources QM: A Multi-Agent Harness Built for Entire Companies
Grounded / Real
Inflated / Uruttu
Original Content
Y Combinator just open-sourced a multiplayer Agent Harness for your entire company 🤯
One agent shared by everyone. Each person uses it privately, teams use it together in Slack.
It's called QM. 100% Open Source under MIT license.
Most agent setups are built like personal assistants. One person, one context. Run that for a whole team and everything collides. Shared credentials, tangled memory, zero permissions.
QM flips the design. Every employee gets an isolated workspace with their own memory, files, keychain, and a durable sandbox where installed tools stay installed. The same agent then shows up in shared Slack channels and projects to work with the team.
And it's harness-agnostic. Claude Code, Codex, OpenCode, and Pi all drive the same core, so your deployment isn't locked to one vendor.
What teams run on it:
• Inbox triage on a schedule, with reply drafts in your writing voice
• Internal web apps the agent builds and publishes to specific people
• Repo work: tests, PRs, CI monitoring
• Crons and watches that keep working while nobody's online
Security comes in three postures. Strict pauses every tool call for human approval. Auto screens external data with a classifier before it reaches the model. Everything is audited under each person's own credentials.
Deploys to your own AWS or Fly account with one command.
My favorite detail: they only accept contributions as written descriptions, not code. You describe the change in a markdown file, the maintainers implement it. One of the four listed contributors is Claude itself.
One agent shared by everyone. Each person uses it privately, teams use it together in Slack.
It's called QM. 100% Open Source under MIT license.
Most agent setups are built like personal assistants. One person, one context. Run that for a whole team and everything collides. Shared credentials, tangled memory, zero permissions.
QM flips the design. Every employee gets an isolated workspace with their own memory, files, keychain, and a durable sandbox where installed tools stay installed. The same agent then shows up in shared Slack channels and projects to work with the team.
And it's harness-agnostic. Claude Code, Codex, OpenCode, and Pi all drive the same core, so your deployment isn't locked to one vendor.
What teams run on it:
• Inbox triage on a schedule, with reply drafts in your writing voice
• Internal web apps the agent builds and publishes to specific people
• Repo work: tests, PRs, CI monitoring
• Crons and watches that keep working while nobody's online
Security comes in three postures. Strict pauses every tool call for human approval. Auto screens external data with a classifier before it reaches the model. Everything is audited under each person's own credentials.
Deploys to your own AWS or Fly account with one command.
My favorite detail: they only accept contributions as written descriptions, not code. You describe the change in a markdown file, the maintainers implement it. One of the four listed contributors is Claude itself.
Validated Content
Y Combinator has genuinely open-sourced QM, a multi-agent harness designed for company-wide AI agent use. QM is released under the MIT license and supports collaborative workflows through Slack and a web interface. The core idea of giving employees more isolated agent environments while allowing teams to collaborate is consistent with the project. However, several technical details in the original post are either simplified or not independently verified, including the exact support for Claude Code, Codex, OpenCode, and Pi, the three specific security postures, one-command AWS/Fly deployment, and the claim that contributions are accepted only as Markdown descriptions. The statement that Claude is one of the listed contributors is also unverified. The examples involving inbox triage, internal apps, PRs, CI monitoring, and scheduled agents are plausible use cases, but shouldn't all be presented as officially confirmed QM features without documentation. Overall, the main announcement is real, but the post adds a significant amount of interpretation and unverified technical detail.