inis.run
For RL & eval teams

Fork one state into hundreds.

Bring an environment to exactly the state you want, then fan it out into parallel children in a single call. Collect the results, pay for the seconds you use.

Fork the exact state

Children start from the same live running point — not a fresh boot re-running setup.

Hundreds in one call

Fan a session out into parallel children, each on its own isolated machine.

Per-second billing

Pay for active compute only. Paused and idle sessions don’t run the clock.

Deterministic baselines

Bring an environment to a known state once, then branch from it as many times as you need.

Built for rollouts

Sweeps, batch evals, RL rollouts — collect results across every child.

Call it from your stack

Python and TypeScript SDKs, the CLI, or remote MCP. No orchestration layer to run.

Fan out your next run.