# MongoHive

- **Event:** [The Harness Engineering & Model Wrangling Hackathon](https://cerebralvalley.ai/e/mongodb-nyc-hackathon)
- **When:** Sat, Sep 26 at 9:00 AM – 10:00 PM (EDT)
- **Where:** New York, NY
- **Team:** [Ani Potts](https://cerebralvalley.ai/u/anipotts), [Kapil Rajpopat](https://cerebralvalley.ai/u/kap-il)
- **GitHub:** https://github.com/anipotts/mongo-hive
- **Demo video:** https://youtu.be/Wrv3Wx8YVvs
- **Gallery:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/19

MongoHive turns what one agent learns into tested tools every teammate's agent can call by name. When your Claude or Codex agent finishes an investigation, a background worker distills it into a reusable, read-only tool persisted in MongoDB Atlas. A teammate's background worker checks it independently, and disagreements go to a human. Promoted tools then appear as named MCP tools in everyone's agent. Versions, evals and promotion live in Atlas, and change streams push updates into each agent's chat.

## More from The Harness Engineering & Model Wrangling Hackathon

- [Levy](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/16)
- [CtrlAltElite](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/17)
- [Reflexes](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/18)
- [Ada](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/20)
- [PolicyPilot](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/21)
- [Moss](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/22)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/19. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt