YC Just Open-Sourced Its Multiplayer AI Agent
Y Combinator just open-sourced QM, the multi-agent harness it uses internally across company work. In this video, I break down what makes QM different from personal agents like Hermes and OpenClaw, then walk through its web workspace, Slack integration, shared memory, keychain, applications, governance, metrics, and audit controls. You’ll see why this “multiplayer” approach could be the next step for teams adopting AI agents.
⏱️ TIMESTAMPS:
0:00 What YC just released 0:10 What QM is 1:47 Why QM works differently 2:57 The user workspace 3:25 Testing the QM agent 4:18 Keychain, apps, memory, and skills 5:12 The company admin dashboard 5:33 Judgments and agent oversight 6:00 Files, skills, and organization memory 7:18 AI usage metrics 7:42 Governance and data boundaries 8:53 Auditing every agent action 9:37 Why multiplayer agents matter 10:15 Setup notes and final takeaways
🔗 CONNECT WITH ME:
💼 LinkedIn: https://www.linkedin.com/in/miguel-torrez/ 🌐 Genial Agency: https://genial-agency.com 🇫🇷 Luwai (French): https://luwai.fr 👤 Personal: https://migueltorrez.ai 📅 Book a chat: https://cal.com/miguel-torrez
🛠️ TOOLS MENTIONED:
• QM: https://github.com/yc-software/qm • QM website: https://qm.ycombinator.com • Slack: https://slack.com • Hermes Agent: https://hermes-agent.nousresearch.com/docs/ • OpenClaw: https://openclaw.ai/ • Claude: https://claude.ai • Codex: https://chatgpt.com/codex • DeepSeek: https://www.deepseek.com
💬 DROP A COMMENT:
Would you run one shared AI-agent system across your whole company, or keep every agent isolated?
#AIAgents #YCombinator #OpenSource #QM
