YC Just Open-Sourced Its Multiplayer AI Agent

Was Sie brauchen

• A coding agent such as Claude Code or Codex to run the install

• An API key for a model (QM does not accept your ChatGPT or Claude subscription yet)

• Optional: a Slack workspace, if you want QM to live in Slack too

Schritt für Schritt

1. 1

   Understand what QM is

   0:10

   QM is YC's open-source agent harness, similar to Hermes Agent or OpenClaw, but built for teams. It lives in a web app and in Slack at the same time, and each project (personal or shared) gets its own memory, files and skills. Cron jobs, skills and memory are included.

   QM GitHub repoKopieren

   https://github.com/yc-software/qm

   QM websiteKopieren

   https://qm.ycombinator.com

2. 2

   Install it with your coding agent

   10:15

   Give the repo link to Claude Code or Codex and ask it to run QM for you. Expect a few changes to run it locally: QM asks for Slack access right away, so tell your agent to skip the Slack connection if you will not use it.

   Prompt for your coding agentKopieren

   Hey, please run this QM instance for me.

3. 3

   Plug in a model through an API key

   3:25

   QM is API-based only: you cannot use your subscription out of the box. Add an API key. I recommend open-source models such as DeepSeek V4 to keep costs down. If you want to use your OpenAI subscription, ask your coding agent to modify QM for it.

4. 4

   Create a project and test the agent

   2:57

   Open the web app. Create a personal project, or a project shared with teammates. Start a new chat and send a test message to check the model responds.

   Test messageKopieren

   Hey, QM, how are you doing?

5. 5

   Set up files, crons, keychain and apps

   3:52

   In your user view: choose whether each file is shared only with the agent or with teammates too. Add cron jobs for scheduled tasks. Use Keychain to share credentials without exposing the key itself. Open Applications to find apps teammates built and use the deploy button at the top.

6. 6

   Review activity in the admin dashboard

   5:12

   Open the admin dashboard to see every session, from the web app and Slack. Open the Judgments tab to see what agents did and the reasons they gave. Check the preloaded skills (including the onboarding skill), organization memory, deployments and everyone's crons.

7. 7

   Track usage in Metrics

   7:18

   Open Metrics to see how many people use the agent, total tokens used and response times.

8. 8

   Set governance and data boundaries

   7:42

   Use Onboarding to add new users. In Governance, set model permissions, credentials and data boundaries so each person only reaches the data they should. Share connectors, manage users and the keychain, then open Audit to see every event and tool call run by members.

9. 9

   Add what is missing

   9:13

   QM is open source, so add any missing feature yourself: ask QM itself, Codex or Claude Code to make the change. My first addition would be subscription login so the agent can run on a subscription instead of API keys.

Als Nächstes ansehen

• 2:47How to Actually Find Any Claude SkillPull skills from GitHub repositories like QM's and install them in your own Claude setup.
• 4:44Claude Tag: Your New AI Employee in SlackCompare a team agent inside Slack, with its own role and permissions for each channel.