Skip to main content

Install & set up

Start hereOne-line installer, prerequisites, and credentials in three steps.

Quickstart

5 minutesRun init → simulate → optimize on your own agent project.

All commands

ReferenceEvery relai command with flags, examples, and failure modes.

​
The loop, at a glance

Everything in RELAI maps onto a four-step cycle. You can run it by hand, or drive it from your coding agent with a plugin.
1

Initialize

From a git-tracked Python project, relai init registers the agent and generates a simulator harness.
2

Create environments & evaluators

Capture behavior to learn or preserve as repeatable learning environments — from a prompt, or from a run log plus feedback. Optionally register benchmark suites.
3

Simulate

relai simulate measures how the agent behaves today against the environments or benchmarks you select.
4

Optimize

relai optimize proposes or applies improvements — and can open a PR with the changes.
New here? Don’t have an agent handy? Run relai onboarding to clone a disposable sample agent and walk the whole loop end-to-end. See Try the sample agent.