# Long Horizon Quant Research

- **Event:** [The Harness Engineering & Model Wrangling #SFTechWeek Hackathon](https://cerebralvalley.ai/e/mongodb-sftw-hackathon)
- **When:** Sun, Oct 11 at 9:00 AM – 10:00 PM (PDT)
- **Where:** San Francisco, CA
- **Team:** [Tehani Cabour](https://cerebralvalley.ai/u/tehanicabour), [Shawn Yang](https://cerebralvalley.ai/u/Shawny)
- **GitHub:** https://github.com/jordandaisy/long-memory-desk
- **Demo video:** https://youtu.be/AoOwNyLTuCc
- **Gallery:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/56

Long-Memory Research Desk is a team of five quant agents that remembers twenty years of markets in MongoDB Atlas and reads live filings, news, prediction markets and social posts, yet retrieves nothing dated after the desk's clock. The agents debate in a shared Strategy Room, backtest each idea only on prices up to the clock, and save the results (Sharpe, drawdown) as lessons that debates years later cite. We built it today for Track 2 (Long Horizon Engineering) on MongoDB Atlas, Claude and TypeSafe AI's Jev through the Vercel AI Gateway, ElevenLabs for the desk's voice, and Raindrop, whose flagged traces Claude turns into playbooks for the agents.

## More from The Harness Engineering & Model Wrangling #SFTechWeek Hackathon

- [SREvolve](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/53)
- [By my self](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/54)
- [PaperTrail](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/55)
- [LLM deployment agent](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/57)
- [LabRat](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/58)
- [Hype](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/59)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/56. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt