Start tracking a project already under way
You have weeks of work in a repository and no record of it. Start the record from what the files say.
Paste this into your agent
Section titled “Paste this into your agent”Run rb init "<the work's theme>" in your own terminal and paste the line it prints:
Record where this repository's work stands now, from its own files.
This is the line rb init prints, word for word.
Use Rabbit Brain to track this: read rb context, then record where the work stands.
The repository we ran it on holds an INT8 post-training quantization of a ResNet-20 on CIFAR-10:
configs/for training, FP32 and INT8- the plan,
docs/plan.md: “INT8 ships if it loses at most 0.5 points of top-1 against FP32.” results/int8-ptq/: three seeds and a report
What you’ll see
Section titled “What you’ll see”Once the agent is done, in your own terminal:
$ rb statusINT8 ResNet-20 on CIFAR-10 · int8-resnet-20-on-cifar-10Kept with rb since 2026-11-10. All 3 runs were recorded afterwards, not as they happened.14 record files not committedLast reconcile, 2026-11-10 15:32 UTC: 1 re-indexed (int8-ptq) · 1 result quoted · 1 next step quoted
Does INT8 lose at most 0.5 points of top-1 against FP32 on CIFAR-10? (open) INT8 loses at most 0.5 points of top-1 against FP32. change.top1: -0.08 [-0.1545, -0.005476] % · paired difference, t interval, 3 seeds, 95% (rb); loss: the interval clear of 0 on the worse side (higher is better); criterion met: estimate -0.08 ≥ -0.5; rule and question link declared after the evidence existed: all 3 units were produced before it was declared. units: 3 seeds. experiment context: int8-ptq · INT8 post-training quantization result: "INT8 top-1 is 91.62 against FP32's 91.70 over three seeds: 0.08 points lower." (README.md:7) next: "Try per-channel calibration with 128 images." (README.md:11) note nrind62: The question is docs/plan.md:3 turned into a question: "INT8 ships if it loses at most 0.5 points of top-1 against FP32." · not confirmed git clean
Rules: 1 met
The design of 1 experiment is not confirmed: rb confirm lists it.
Facts that ask for nothing (1) - int8-ptq: 1 criterion was declared after its evidence existed
rb looks in out/, outputs/, results/, eval-out/ and metrics/ at the top, in folders named for results (results/, eval/, metrics/, reports/, artifacts/ and the like), down to 4 levels from the top, at the files in the repository's top folder, and at .json, .yaml and .toml files git shows as new or changed. It last looked at 2026-11-10 15:32 UTC. It reads what code, configs, docs and database rows say only where the record points to them, and it sees only the commands run through rb journal run.rb checked the record with git at 2026-11-10 15:32 UTC: all 14 record files are new, changed or deleted since commit 93d9471a93e2, which does not hold the record.Not committed: .rb/.gitattributes (new), .rb/.gitignore (new), .rb/experiments/int8-ptq/criteria/top1-drop-budget.yaml (new) and 11 moreTo check it yourself, in your terminal: git -C ~/int8-resnet status --short --untracked-files=all -- .rb
Rules top1-drop-budget INT8 loses at most 0.5 points of top-1 against FP32 criterion met · loss · change.top1 ≥ -0.5 reads: change.top1: -0.08 [-0.1545, -0.005476] % · paired difference, t interval, 3 seeds, 95% (rb) result: loss: the interval clear of 0 on the worse side (higher is better) rule: criterion met: estimate -0.08 ≥ -0.5 timing: declared after the evidence existed: all 3 units were produced before it was declared units: 3 seeds
Experiments int8-ptq INT8 post-training quantization · open · fp32 (baseline) vs int8 (candidate) · varies precision, calib_images · not frozen · settings 7 verified · 0 provisional · 0 unknown · 1 per-run · runs 3 to run again: code unknown · environment unknown · files ok
Runs: 3 recorded on 1 experiment · every receipt is what rb wrote
Next: rb confirmtop1-drop-budget is the id of the plan’s criterion, a rule the runs are checked against.
The experiment shows “code unknown · environment unknown” because the runs were made before rb was watching.
The experiment’s design stays the agent’s until you confirm it as yours:
$ rb confirmDesigns waiting for a confirmation (1): int8-ptq: INT8 post-training quantization questions: q-int8 hypothesis or purpose: not recorded why: not recorded variants: fp32 (baseline), int8 (candidate) · varies precision, calib_images setting optim.lr: 0.1 from configs/train.yaml#optim.lr setting optim.momentum: 0.9 from configs/train.yaml#optim.momentum setting data.batch_size: 128 from configs/train.yaml#data.batch_size setting eval.batch_size: 256 from configs/train.yaml#eval.batch_size setting seed: per run setting fp32.precision: "fp32" from configs/fp32.yaml#precision setting int8.precision: "int8" from configs/int8.yaml#precision setting int8.calib_images: 512 from configs/int8.yaml#calib_images criterion top1-drop-budget (primary): change.top1 ≥ -0.5 · for q-int8 confirm: rb confirm int8-ptq@775110fdf0ef6a94a6d1aa30ed23b790454a0151cf4aa4f991f701e30af6773c note nrind62 on int8-ptq stays not confirmed: a note is not part of the design. To say one as yours, write it in your own terminal: rb note add "<its words>" -e int8-ptq, then rb retract <note> --why "<reason>".$ rb confirm int8-ptq@775110fdf0ef6a94a6d1aa30ed23b790454a0151cf4aa4f991f701e30af6773cint8-ptq's design is confirmed. note nrind62 on int8-ptq stays not confirmed: a note is not part of the design. To say one as yours, write it in your own terminal: rb note add "<its words>" -e int8-ptq, then rb retract <note> --why "<reason>".
Next: rb statusWhat rb did, step by step
Section titled “What rb did, step by step”-
Read the briefing
rb contextpoints the agent atrb docs --start, the protocol for a project already under way:Terminal window $ rb context# The record: INT8 ResNet-20 on CIFAR-10## First, record where the work standsNothing is recorded yet, and this project holds work already done: 2 commits and 1 results folder. Record where the work stands now, in this turn, from the files, and ask the researcher nothing first. How: rb docs --start.… (57 more lines) -
Read what the repository already says
rb reconcilequotes the report in each results folder word for word. It writes nothing.Terminal window $ rb reconcileThe repository at commit 93d9471a93e2: 1 results folder.int8-ptq results/int8-ptq/ new, not in the recordtitle: "INT8 post-training quantization" (README.md:1)says: "Three seeds of FP32 and INT8, evaluated with `python eval.py --seed <N>`." (README.md:3)result: "INT8 top-1 is 91.62 against FP32's 91.70 over three seeds: 0.08 points lower." (README.md:7)next: "Try per-channel calibration with 128 images." (README.md:11)files: 1 report · 6 results filesgit: all 7 report and results files are tracked · folder unchanged since the last commitrb reconcile --apply keeps this in the record: 1 experiment to add. -
Record the question and the experiment
Terminal window $ rb question add "Does INT8 lose at most 0.5 points of top-1 against FP32 on CIFAR-10?" --id q-int8q-int8: Does INT8 lose at most 0.5 points of top-1 against FP32 on CIFAR-10?Next: rb experiment add "<what would answer it>" -q q-int8 --hypothesis "<what you expect>"Terminal window $ rb experiment add "INT8 post-training quantization" --id int8-ptq -q q-int8 --baseline fp32 --candidate int8 --varies precision,calib_imagesExperiment int8-ptq: INT8 post-training quantization · fp32 (baseline) vs int8 (candidate) · varies precision, calib_images · under q-int8Planned: nothing in the record tests it yet, and it shows as a planned direction until its first run or analysis.Made 2 variants: fp32 (baseline), int8 (candidate); a setting of one is rb spec set int8-ptq fp32.<setting> <value>.int8-ptq declares it varies precision, but no variant has a value for it yet; give each variant its own: rb spec set int8-ptq <variant>.precision <value> --source <file#key>int8-ptq declares it varies calib_images, but no variant has a value for it yet; give each variant its own: rb spec set int8-ptq <variant>.calib_images <value> --source <file#key>Next: rb spec set int8-ptq --from <config.yaml> --keys "<the keys that define it>" · rb criterion add "<what it should show>" -e int8-ptq -q q-int8 --metric <name> --at-most <x> -
Cite every setting to the file that states it
Terminal window $ rb spec set int8-ptq --from configs/train.yaml --keys "optim.*,data.*,eval.*"int8-ptq: 4 settings from configs/train.yaml @93d9471a93e2 · 4 verified$ rb spec set int8-ptq fp32.precision fp32 --source "configs/fp32.yaml#precision"int8-ptq/fp32.precision = fp32 · verified in configs/fp32.yaml#precision$ rb spec set int8-ptq int8.precision int8 --source "configs/int8.yaml#precision"int8-ptq/int8.precision = int8 · verified in configs/int8.yaml#precision$ rb spec set int8-ptq int8.calib_images 512 --source "configs/int8.yaml#calib_images"int8-ptq/int8.calib_images = 512 · verified in configs/int8.yaml#calib_images$ rb spec set int8-ptq seed --per-runint8-ptq/seed · per-run: each run gives its own, with --set seed=<value> on rb run add -
Record the plan’s criterion, cited to its line
rb checks that
docs/plan.md:3is there and states the criterion’s threshold.Terminal window $ rb metric add top1 --unit % --maximizeMetric top1 (%): higher is betterTerminal window $ rb criterion add "INT8 loses at most 0.5 points of top-1 against FP32" -e int8-ptq -q q-int8 --metric change.top1 --at-least -0.5 --why docs/plan.md:3 --id top1-drop-budgettop1-drop-budget: INT8 loses at most 0.5 points of top-1 against FP32change.top1 ≥ -0.5 · primary · on int8-ptqdeclared; no evidence recorded yetNext: rb run add int8-ptq --from <the results file a run wrote> --set seed=<value> -
Record each run from its own file
Terminal window $ rb run add int8-ptq --from results/int8-ptq/seed1/metrics.json --set seed=1 --config results/int8-ptq/seed1/config.yamlrunrpxwux on int8-ptq: fp32.top1=91.71, int8.top1=91.6 · seed=1Ran with the spec: 5 of its settings found in results/int8-ptq/seed1/config.yaml, all matching.Produced: 2026-10-20 10:00:00 (file)top1-drop-budget estimate meets criterion · point only: change.top1: -0.11 % · paired difference, 1 seed (rb)rb put the code in git at refs/rb/snapshots/49a2f7fb6a172a9a46a4624957355aec6732c343, so it outlives a deleted branch or worktree; git update-ref -d refs/rb/snapshots/49a2f7fb6a172a9a46a4624957355aec6732c343 removes it.Next: rb show top1-drop-budget$ rb run add int8-ptq --from results/int8-ptq/seed2/metrics.json --set seed=2 --config results/int8-ptq/seed2/config.yamlrunhc2lw2 on int8-ptq: fp32.top1=91.66, int8.top1=91.58 · seed=2Ran with the spec: 5 of its settings found in results/int8-ptq/seed2/config.yaml, all matching.Produced: 2026-10-20 10:00:00 (file)top1-drop-budget estimate meets criterion · point only: change.top1: -0.095 % · paired difference, 2 seeds (rb)Next: rb show top1-drop-budget$ rb run add int8-ptq --from results/int8-ptq/seed3/metrics.json --set seed=3 --config results/int8-ptq/seed3/config.yamlrun4ssgrk on int8-ptq: fp32.top1=91.74, int8.top1=91.69 · seed=3Ran with the spec: 5 of its settings found in results/int8-ptq/seed3/config.yaml, all matching.Produced: 2026-10-20 10:00:00 (file)top1-drop-budget criterion met · loss: change.top1: -0.08 [-0.1545, -0.005476] % · paired difference, t interval, 3 seeds, 95% (rb)Next: rb show top1-drop-budget -
Keep what the report says
Terminal window $ rb reconcile --applyThe repository at commit 93d9471a93e2: 1 results folder.Kept in the record: 1 re-indexed (int8-ptq) · 1 result quoted · 1 next step quoted.int8-ptq results/int8-ptq/ in the recordtitle: "INT8 post-training quantization" (README.md:1)says: "Three seeds of FP32 and INT8, evaluated with `python eval.py --seed <N>`." (README.md:3)result: "INT8 top-1 is 91.62 against FP32's 91.70 over three seeds: 0.08 points lower." (README.md:7)next: "Try per-channel calibration with 128 images." (README.md:11)files: 1 report · 6 results filesgit: all 7 report and results files are tracked · folder unchanged since the last commit
Runs kept another way
Section titled “Runs kept another way”- Each run in its own folder: Record a folder per run.
- Runs as rows of one table, such as
results.tsv: Record one table of many runs.
Rabbit Brainrabbitbrain.ai · GitHub · PyPI · Privacy · Apache-2.0