Install
rb needs Python 3.10 or later. The package is rabbit-brain and the command is rb. Wheels cover Linux (x86_64, aarch64), macOS (Apple Silicon, Intel) and Windows (x86_64).
On Windows, rb 0.8.4 is a preview. See issue #2 for known issues.
In a project’s environment, where you can also import rabbit_brain:
pip install rabbit-brainAs a tool, in its own environment:
uv tool install rabbit-brainWithout installing:
uvx --from rabbit-brain rb tourrb is then not on your path. Run later commands as uvx --from rabbit-brain rb <command>.
Check it:
$ rb --versionrabbit-brain 0.8.4Take the tour
Section titled “Take the tour”rb tour builds a small project in ./rb-tour and takes it from a question to three runs. It prints every command with its real output:
$ rb tour
$ rb init 'Dropout on a tiny MLP'Project 'dropout-on-a-tiny-mlp' started: ~/try-rb/rb-tour/.rbRabbit Brain YAML files beside the code: commit .rb/ with it, so the record travels with the work.
For the agents here: No agent's instructions here yet. rb skill add puts rb's for one: --claude (Claude Code), --agents-md (Codex and others), --cursor
Then paste this line into your agent's chat: Use Rabbit Brain to track this: read rb context, then record where the work stands.
$ rb question add 'Can we use dropout 0.1 within our loss and step-time budgets?' --id q1q1: Can we use dropout 0.1 within our loss and step-time budgets?
Next: rb experiment add "<what would answer it>" -q q1 --hypothesis "<what you expect>"
$ rb experiment add 'dropout 0.1 vs none' --id drop -q q1 --hypothesis 'Dropout 0.1 lowers val_loss' -m 'less co-adaptation' --baseline none --candidate p01 --varies dropout --note 'assumes the validation split stayed fixed'Experiment drop: dropout 0.1 vs none · none (baseline) vs p01 (candidate) · varies dropout · under q1 hypothesis: Dropout 0.1 lowers val_loss (why: less co-adaptation) Planned: nothing in the record tests it yet, and it shows as a planned direction until its first run or analysis. Made 2 variants: none (baseline), p01 (candidate); a setting of one is rb spec set drop none.<setting> <value>. drop declares it varies dropout, but no variant has a value for it yet; give each variant its own: rb spec set drop <variant>.dropout <value> --source <file#key>… (137 more lines)Then cd rb-tour and run rb ui (terminal) or rb open (browser) to look around.
Updates
Section titled “Updates”Installed as a tool (uv tool install or pipx install), rb upgrades itself through that installer, at most once a day.
Installed with pip, rb never touches the environment. When a newer release is out, it prints a one-line notice instead, at most once a day.
Neither runs in CI, in an agent session, with DO_NOT_TRACK set, with RB_AUTO_UPDATE=0, or after rb config auto-update off. The update check carries nothing about you.
A team on two versions
Section titled “A team on two versions”rb 0.8.4 saves some rules in format 2, which rb 0.7.0 and 0.7.1 cannot read. Upgrade everyone who shares a record together. The record’s format has the details.
What rb sends, and when
Section titled “What rb sends, and when”rb needs the network only for:
rb clone, which fetches a bundle and the code it namesrb login,rb syncandrb logout, which connect to rabbitbrain.ai or a hub you name- the daily update check
- usage analytics, once you run
rb telemetry enablein your own terminal
Analytics never carry research content, paths, command arguments or names. rb telemetry preview shows what would be sent. DO_NOT_TRACK=1 or RB_TELEMETRY=0 keeps them off.
Uninstall
Section titled “Uninstall”rb remove takes out only rb’s parts: the record, its agent instructions and its hook handlers. Your research files and git history stay. rb remove --dry-run shows what it would do first. Then run pip uninstall rabbit-brain or uv tool uninstall rabbit-brain.
Rabbit Brainrabbitbrain.ai · GitHub · PyPI · Privacy · Apache-2.0