Skip to Main Content

Many Lives

Built at The Harness Engineering & Model Wrangling Hackathon · Sep 26, 2026 · New York, NY

Demo video · drive.google.com/…

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.

Team