# Rabbit Brain docs > Rabbit Brain (rb) keeps the record of the ML experiments you run with coding agents, as plain YAML in .rb/ next to your code. If a project has a .rb/ directory, run `rb context --model ` before anything else: it is the state of the work. The full manual is built into rb: `rb docs`. Every page below but the Changelog as one file: https://rabbitbrain.ai/docs/llms-full.txt ## Pages - [Rabbit Brain docs](https://rabbitbrain.ai/docs/): Know where your research stands. Your AI agent records what was tried, what the results show, and what's still open, with the code and settings. - [Install](https://rabbitbrain.ai/docs/install/): Install rb from PyPI and take the one-minute tour. - [Your first record](https://rabbitbrain.ai/docs/first-record/): Start the record in your repository, then paste one line into your coding agent. - [Connect your agent](https://rabbitbrain.ai/docs/connect/): What rb installs for Claude Code, Codex and Cursor, and how to use rb without an agent. - [The record](https://rabbitbrain.ai/docs/concepts/record/): Plain YAML files in .rb/, committed with your code. They hold the questions, experiments, runs and calls. - [Criteria](https://rabbitbrain.ai/docs/concepts/criteria/): A criterion is the rule a result must meet. rb records who declared it and when. - [Findings](https://rabbitbrain.ai/docs/concepts/findings/): How rb computes a finding from the runs, and what each line of it says. - [Calls](https://rabbitbrain.ai/docs/concepts/calls/): A call is a decision on a result or a line of work. An agent's call waits for your confirmation. - [Sharing](https://rabbitbrain.ai/docs/concepts/sharing/): Send a record's page, or publish the whole record so others can clone and rerun it. - [Cookbooks](https://rabbitbrain.ai/docs/cookbooks/): Eleven tasks, each with the prompt to paste into your coding agent and rb's real output from running it. - [Start tracking a project already under way](https://rabbitbrain.ai/docs/cookbooks/project-under-way/): Record where the work stands from the repository's own files, in one turn, with no questions asked first. - [Record one table of many runs](https://rabbitbrain.ai/docs/cookbooks/one-table/): Record each row of a results table as its own run, with one command per arm. - [Record a folder per run](https://rabbitbrain.ai/docs/cookbooks/run-folders/): Record each run folder from its own config and metrics. rb reconcile prints the command for each. - [Check a summary's claims against the runs](https://rabbitbrain.ai/docs/cookbooks/check-a-summary/): Check each claim in an agent's summary against the runs it is about. - [Declare the criterion before the runs](https://rabbitbrain.ai/docs/cookbooks/criterion-before-runs/): Declare what counts and freeze it before the first run, so rb shows the criterion came first. - [Compare against a published baseline](https://rabbitbrain.ai/docs/cookbooks/published-baseline/): Cite the paper's number and settings. rb says reproduced or not, and does not compare when a setting differs. - [Get an interval, not a single number](https://rabbitbrain.ai/docs/cookbooks/interval-from-seeds/): Run seeds until the criterion has the interval it needs, and read what rb says after each one. - [Read a rule over seeds](https://rabbitbrain.ai/docs/cookbooks/rules-over-seeds/): A count, a best of N and a relative change over five seeds, and how rb reads each. - [Share the record, and rerun it](https://rabbitbrain.ai/docs/cookbooks/share-a-record/): Send someone a page of your record, and a bundle their agent can clone and rerun. - [Rerun a run from its receipt](https://rabbitbrain.ai/docs/cookbooks/rerun-from-receipt/): A run's receipt names its command and commit. Rerun it on that commit and record it as a check. - [rb with Claude Code, Codex and Cursor](https://rabbitbrain.ai/docs/cookbooks/three-agents/): What rb installs for Claude Code, Codex and Cursor, so all three write to the same record. - [The CLI](https://rabbitbrain.ai/docs/reference/cli/): Every rb command, with its help exactly as rb prints it. - [Commands: The record](https://rabbitbrain.ai/docs/reference/cli/the-record/): Commands that start the record (.rb/) and write to it. - [Commands: Calls](https://rabbitbrain.ai/docs/reference/cli/calls/): Lock an experiment before its evidence, record or confirm a call, and take anything back. - [Commands: Reading it](https://rabbitbrain.ai/docs/reference/cli/reading/): Read the record in your browser or terminal, as a briefing for an agent, or as one HTML file. - [Commands: Carrying it](https://rabbitbrain.ai/docs/reference/cli/carrying/): Export the project, start your own work from an exported bundle, and check this machine against the runs. - [Commands: For agents](https://rabbitbrain.ai/docs/reference/cli/for-agents/): Commands a coding agent uses: the MCP server, the skill, the journal, reconcile and compile. - [Commands: Upkeep](https://rabbitbrain.ai/docs/reference/cli/upkeep/): Check the record and format its files. Manage rb's own settings and optional usage analytics. - [Commands: Leaving](https://rabbitbrain.ai/docs/reference/cli/leaving/): Take rb out of a checkout, removing only what rb can tell is its own. - [Commands: Reference](https://rabbitbrain.ai/docs/reference/cli/reference/): The tour, the manual, the record's format, the version and the feedback link. - [Commands: rabbitbrain.ai](https://rabbitbrain.ai/docs/reference/cli/rabbitbrain-ai/): Sign this machine in to rabbitbrain.ai, keep a private copy of the record's page there, and sign out. - [The record's format](https://rabbitbrain.ai/docs/reference/schema/): The format of the files in .rb/ and their JSON Schema. - [Changelog](https://rabbitbrain.ai/docs/changelog/): What each release of rb changed, newest first, from rb's own CHANGELOG.md. - [llms.txt](https://rabbitbrain.ai/docs/agents/llms-txt/): Where an agent finds rb's docs, and what it must not do. - [Auth](https://rabbitbrain.ai/docs/agents/auth/): How rb signs a machine in to rabbitbrain.ai or another hub, and what an agent must leave alone.