Know where your research stands.
git status shows which files you changed. rb status shows which results met their pass mark.
Quick start: a sample study
Section titled “Quick start: a sample study”Try Rabbit Brain on a sample study, so you don’t need to set up any experiments or use your own research. Just open Claude Code or Codex in an empty folder and paste the prompt below.
Sample study
Clone https://github.com/rabbit-brain/think-step-by-step and work inside it. Install rabbit-brain from PyPI into a virtual environment in that folder. It's open source: https://github.com/rabbit-brain/rb Start rb login in the background and show me the sign-in link it prints. I'll sign in. When I'm signed in, run rb sync and give me the link it prints. Run rb context and tell me in three lines what the study found and what's still open. Don't run any experiments.
Your agent gives you a sign-in link (an email code, no password). Then the study opens in your private account on rabbitbrain.ai. No account? Ask your agent to run rb page instead.
What rb shows you
Section titled “What rb shows you”In the warmup cookbook, the plan says warmup must lower validation loss by at least 0.02 nats. Over 3 seeds it lowered it by 0.028, so the rule is met. The rule was written before the runs, and rb says so.
$ rb show warmup-helpsCriterion warmup-helps on warmup (primary, own): Warmup lowers final validation loss by at least 0.02 nats warmup-helps Warmup lowers final validation loss by at least 0.02 nats criterion met · gain · change.val_loss ≤ -0.02 (n ≥ 3) reads: change.val_loss: -0.02767 [-0.03484, -0.0205] nats · paired difference, t interval, 3 seeds, 95% (rb) result: gain: the interval clear of 0 on the better side (lower is better) rule: criterion met: estimate -0.02767 ≤ -0.02 timing: declared before the evidence (by production times) units: 3 seeds integrity: ok runttgab7: difference -0.031 (file) · unit seed=1 · seed=1 runvw3726: difference -0.026 (file) · unit seed=2 · seed=2 run2ugudg: difference -0.026 (file) · unit seed=3 · seed=3The loop
Section titled “The loop”-
Your agent records the work
Run
rb init "<the work's theme>"in your repository, then paste this into your agent:Use Rabbit Brain to track this: read rb context, then record where the work stands. -
rb checks and works out the results
When the agent records 500 for
warmup_steps, rb checks thatconfigs/warmup.yamlsays 500 too. Each result is worked out from the runs whenever you runrb statusorrb show. -
You decide
You accept or reject a result with
rb decideand your reason. A decision your agent records waits until you runrb confirmin your own terminal.
Try it in a minute
Section titled “Try it in a minute”rb tour builds a small example project in ./rb-tour and shows each command with rb’s real output. With uv, nothing gets installed:
uvx --from rabbit-brain rb tour$ rb tour…That is the loop, and rb-tour/.rb/ is an ordinary record, YAML files you can read: poke at it.One criterion meets its rule: three seeds, declared and frozen before the runs, every setting with its source.The other is undetermined: two seeds report step_ms and it asks for three. rb will not round that up, and neither should anyone.
Keep going, in the record: cd rb-tour rb ui your screen in this terminal rb open the same, in your browser rb page the record as one HTML file rb export the page to publish, the record if asked rb docs the whole manual rb skill add teach your coding agent the discipline…Where to go next
Section titled “Where to go next”Install rb, or let your agent do it, then take the one-minute tour.
Get startedYour first recordRun rb init in your repository and paste the line it prints into your agent.
One YAML file per run or rule, in .rb/. Each setting keeps the file it came from.
Eleven tasks with prompts to paste, such as checking an agent’s summary against its runs.
ReferenceThe CLIEvery command’s --help, exactly as rb prints it.
An agent reads the manual with rb docs. It must never edit .rb/ by hand.
Rabbit Brainrabbitbrain.ai · GitHub · PyPI · Privacy · Apache-2.0