Skip to main content
GBrain
Menu
Get Started

QM

Y Combinator's QM, sharing one memory with every AI the team uses.

Y Combinator's open-source harness for a whole company, with the team's memory and tools added.

QM is built for a whole company rather than one person: each person and each room gets its own scoped memory, files and permissions, in Slack and on the web.

A QM admin registers GBrain as one of its MCP servers with the request below, and every agent in the deployment can reach the workspace’s memory and the accounts connected to it: mail, calendar, web search and page fetching, at the level the team sets.

The memory stays the workspace’s. The same notes answer in QM, in ChatGPT and in Claude, so switching tools does not start anyone over.

One endpoint connects QM

Not one per service. What this client can call is decided by its permission, not by the address, and the token comes from the client's own page in the workspace, minted once and shown once.

Request
PUT /v1/admin/mcp-servers/gbrain
Body
{
  "name": "GBrain",
  "url": "https://gbrain.io/mcp",
  "auth": "bearer",
  "bearerToken": "<token>",
  "readOnly": false,
  "enabled": true
}

QM runs a server marked read-only in its read-only turns too. GBrain can write, to memory and to the accounts connected to it, so it is registered with readOnly false.

Every application QM gets

Connect one in the browser and it answers here, under the same permission and the same record as everywhere else.

The other places a connection answers are on Works with, and Tools explains the permission, the ceiling and the record they share.