A Rust runtime that journals every step an agent takes, so it survives any crash and replays exactly, nondeterministic model behavior included.
Durable execution made software reliable. But its replay model assumes determinism, and LLM agents are not deterministic. Everyone else caches around that. Pragmatic models it.
Each model turn's realized outcome is recorded to an append-only log as the run proceeds, tool calls and token usage included. The journal is the source of truth for what the agent actually did, not a reconstruction after the fact.
Resume exactly where the agent stopped. Recorded outcomes are read back instead of re-sampled, so there are no duplicate model calls, no re-executed tools, and no lost work after a failure.
Reproduce the entire run exactly for debugging and audit, nondeterministic LLM behavior included. Replaying the journal reproduces the original trace, exactly, every time.
Tell us what you're building.