# Many Lives

- **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:** [Mike Sandare](https://cerebralvalley.ai/u/msandare), [Niraj Amalkanti](https://cerebralvalley.ai/u/RedoubtWarden), [Harry Singh](https://cerebralvalley.ai/u/harrypahwa)
- **GitHub:** https://github.com/HarryPahwa/Many-Lives
- **Demo video:** https://drive.google.com/drive/folders/1J_7vYpNcmb6lpu1cV5rhMlVdCYe7k60z
- **Gallery:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/92

Many-Lives is a persistent-world agent harness, demonstrated by a turn-based text dungeon. The harness is the product; the game is the environment.

It solves the problem that LLM "agents" usually live in a chat transcript: continuity depends on replaying history, context grows without bound, and the model is trusted to report its own effects. Many-Lives inverts that. Models interpret, propose, describe and reason; only deterministic application code may establish or mutate canonical state. No model has database-write access. Player text is an attempted action, never an authority, so prompt-injection attempts change nothing. Dice come from seeded code RNG. Narration is generated after commit and can never alter state. Repeating a turn id returns the stored result and applies nothing.

Continuity comes from stored state, not a transcript: kill the server mid-raid, restart, and the same world resumes. Measured result: stored history grew 100x (100 to 10,000 events, 3.8 MB) while the context assembled for one model call moved from 239 to 246 tokens — 1.03x, against a 3000-token budget. Reproducible with scripts/seed_stress_history.py.

## More from The Harness Engineering & Model Wrangling Hackathon

- [Wrasse](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/89)
- [Reconcile](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/90)
- [Pheonix](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/91)
- [UltraPM Console](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/93)
- [Btechs](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/94)
- [Casefile](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/95)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/92. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt