Learnabolic

give AI agents (recursive) self-improvement

Your 👍 is the gradient.

Watch it learn → GitHub

No API key. No model. ~150 lines of math.

live sim · gen 0 · fitness —

§ 02 · use it in 60 seconds

Install. Tell your agent. Score each use.

  1. Install the skill

    Claude Code, Codex, Cursor and any agent that can run shell commands. Node ≥ 20.

  2. Name the skill to improve

    “Track my commit-message skill with learnabolic and learn from my ratings.”

    Your agent snapshots that skill as v0. Before every use it runs pick and follows the version it gets.

  3. Score every use

    Rate it
    Say “8/10” or 👍. Your agent runs score commit-message 8.
    Let your tests score it
    Add - tests (w=1): auto higher to .learnabolic/bugfix/goals.md, then say: “after each fix, run the tests and score how many pass.” Your agent runs score bugfix 42 --kr tests. auto ranks each count against your last 50 runs, so any suite size works.
    Or say nothing
    Output you accept unchanged scores top marks; output you rewrite scores bottom.

A real run, replayed. You only rate; the statistics decide.

claude code · your project
learnabolic · commit-message

champion v0 gen 0

challengersreject ◂ evidence ▸ promote

your ratings0 uses

Loading the recorded run…

A recorded CLI run, loaded when you scroll here.
learnabolicp. 02 / 13

§ 03 · how it improves itself

Every use is a tiny, safe experiment.

  1. PickYour agent asks which version to follow: usually the champion, sometimes a challenger with one small edit.
  2. ScoreYou, your tests or a stopwatch give that use a number. Nothing else is measured.
  3. RatchetA challenger replaces the champion only once it wins on enough scores. Losers are dropped, so nothing worse ships.
  4. ProposeLearnabolic picks the kind of edit that paid off before. Your agent writes the next small edit.
Where it applies: skills, how to score them, and the goals.md line to add
SkillScore it withgoals.md lineAn edit it might keep
Commit messagesyour 0–10 rating- quality (w=1): 0..10 higher target 8+ Keep the subject under 50 characters.
Bug fixestests passing after the fix- tests (w=1): auto higher+ Reproduce the bug with a failing test first.
SQL queriesquery time in ms- speed (w=1): 0..2000 lower target 500+ Filter rows before joining.
Code reviewaccepted as-is vs. edited- quality (w=1): 0..10 higher target 8+ Lead with the one blocking issue.
Support replies👍 / 👎- thumbs (w=1): 0..1 higher+ Link the exact docs page.
Landing copyconversion %- conversion (w=1): 0..10 higher target 4+ State the price above the fold.

The edits are examples. Which ones survive is decided by your scores, not by the model.

learnabolicp. 03 / 13

§ 04 · the problem

learnabolicp. 04 / 13

§ 05 · the idea

The LLM proposes, statistics disposes.

agent
gate
RejectPromote

kept 0 · n = 0

learnabolicp. 05 / 13

§ 06 · any score

If you can measure it, or rate it, learnabolic can use it to improve your agent.

goals.md
- thumbs (w=1): 0..1 higher
- quality (w=1): 0..10 higher target 8
- speed (w=0.3): 0..2000 lower target 500
- tests (w=0.5): auto higher
- conversion (w=1): 0..10 higher target 4
learnabolicp. 06 / 13

§ 07 · the four instruments

Counting, not judging.

Thompson

Bets on promising candidates without starving the rest.

Q-direction

Learns where to push: tighten, prune, explore…

SPRT ratchet
RejectPromote

Keeps a change only when the evidence says so. Then never slips back.

CUSUM

Notices when it's stuck, then explores.

Why no LLM judge? Judges drift, flatter and cost tokens. Counting doesn't.

learnabolicp. 07 / 13

§ 08 · goals steer

Goals steer; humans own the North Star.

GoalsetpointScoresensorGaperrorDirectioncontrollerSmall editactuator
learnabolicp. 08 / 13

§ 09 · live lab

Watch it learn, live.

Pick two: Correct, Fast, Cheap. Then watch it learn your taste.

Open the full Lab →

learnabolicp. 09 / 13

§ 10 · portable brains

A brain is just a SKILL.md.

learned/sim/SKILL.md
---
name: sim
description: Correct, Fast, Cheap, learned in the Learnabolic Lab.
---
# Coding habits

Strength 0–1: how often the agent does it.

- Write a failing test first (0.00)
- Read the whole file before editing (0.80)
- Reuse existing helpers (0.86)
- Answer in one pass, skip re-checks (0.65)
- Keep diffs small (0.90)
- Run the full test suite after each change (0.00)

```learnabolic
{
  "version": 1,
  "generation": 15,
  "q": {
    "correct|flat": {
      "tighten": -0.025210390978246677,
      "emphasize-weakest-kr": -1.1091207952387683,
      "add-example": -1.0645384726967049,
      "explore": -0.982775643811597,
      "reorder": -1.0641952393127705,
      "prune": -0.9308111040422842
    },
    "cheap|flat": {
      "reorder": 0.032225360000000036,
      "emphasize-weakest-kr": 0.71245,
      "prune": 0.6944916666666667
    },
    "cheap|up": {
      "emphasize-weakest-kr": 1.1748835466666667,
      "add-example": 0.7455333333333333
    },
    "correct|up": {
      "tighten": 0.26,
      "prune": -0.4193918852993734,
      "add-example": -0.6080166121583175,
      "reorder": 0.0002642267989333702,
      "emphasize-weakest-kr": 0.20865139337578326
    },
    "correct|down": {
      "explore": 0.07474889337578339,
      "reorder": -0.16130464764556363,
      "tighten": 0.2262
    }
  },
  "fitnessHistory": [
    0.4185510699338983,
    0.4185510699338983,
    0.4185510699338983,
    0.45532911077564897,
    0.45109968371782677,
    0.5018051015800572,
    0.5266047328662946,
    0.5612413968448526,
    0.5669307372621828,
    0.557596907934775,
    0.5585242915724078,
    0.6092103185292265,
    0.6092103185292265,
    0.6174896901796522,
    0.6162652688199115,
    0.6138004345546706,
    0.6136325305840912,
    0.6106750113707854,
    0.6198476205184079,
    0.6180247546058769,
    0.6255667654796718,
    0.6181568701494322,
    0.6215617878817765,
    0.619442200916749,
    0.607366959403693,
    0.6411773383895388,
    0.6359955905763048,
    0.6379649423819049,
    0.6386553534693458,
    0.6319588084946842,
    0.6329792371079757,
    0.6355738064204125,
    0.6441623791654043,
    0.6342062666545438,
    0.631232542246862,
    0.6362995909343356,
    0.6362995909343356,
    0.6335094530591927,
    0.6336436805565426,
    0.640184509563759,
    0.6406878297946912,
    0.6382962556595023,
    0.6344966209934009,
    0.6344966209934009,
    0.6223205991350939,
    0.6259578231945959,
    0.624484599802904,
    0.6211752227754676,
    0.6279557349626201,
    0.6274239766174715,
    0.6496465854163999,
    0.6516629148912165,
    0.6499306901356137,
    0.6422274596899268,
    0.6407615429200538,
    0.6389557298861409,
    0.6442408077179567,
    0.6459147492824876,
    0.64841378815384,
    0.6491813703265527,
    0.5994536694873139,
    0.6368341073170858,
    0.6401019241396293,
    0.637838009538097,
    0.6520293641285502,
    0.6439441601857132,
    0.6438240474467677,
    0.6438240474467677,
    0.6466825113699703,
    0.6512035790895015,
    0.6512078356774467,
    0.6458368213654477,
    0.627979660364941,
    0.6425688866957622,
    0.6373025465780262,
    0.6365413416518353,
    0.6346643904156101,
    0.6392552349591598,
    0.6499623191539247,
    0.6475799983748709,
    0.6482736137896145,
    0.6481647795950469,
    0.6449799291120413,
    0.6490772212601349,
    0.64643596073202,
    0.64643596073202,
    0.6452874961604277,
    0.6426935572176797,
    0.6529444391477058
  ],
  "lineage": [
    {
      "id": "v0",
      "parent": null,
      "direction": null,
      "generation": 0
    },
    {
      "id": "v6",
      "parent": "v0",
      "direction": "emphasize-weakest-kr",
      "generation": 1
    },
    {
      "id": "v9",
      "parent": "v6",
      "direction": "emphasize-weakest-kr",
      "generation": 2
    },
    {
      "id": "v12",
      "parent": "v9",
      "direction": "reorder",
      "generation": 3
    },
    {
      "id": "v14",
      "parent": "v12",
      "direction": "add-example",
      "generation": 4
    },
    {
      "id": "v17",
      "parent": "v14",
      "direction": "emphasize-weakest-kr",
      "generation": 5
    },
    {
      "id": "v21",
      "parent": "v17",
      "direction": "emphasize-weakest-kr",
      "generation": 6
    },
    {
      "id": "v26",
      "parent": "v21",
      "direction": "prune",
      "generation": 7
    },
    {
      "id": "v41",
      "parent": "v26",
      "direction": "reorder",
      "generation": 8
    },
    {
      "id": "v45",
      "parent": "v41",
      "direction": "explore",
      "generation": 9
    },
    {
      "id": "v56",
      "parent": "v45",
      "direction": "tighten",
      "generation": 10
    },
    {
      "id": "v61",
      "parent": "v56",
      "direction": "tighten",
      "generation": 11
    },
    {
      "id": "v73",
      "parent": "v61",
      "direction": "explore",
      "generation": 12
    },
    {
      "id": "v85",
      "parent": "v73",
      "direction": "tighten",
      "generation": 13
    },
    {
      "id": "v88",
      "parent": "v85",
      "direction": "tighten",
      "generation": 14
    },
    {
      "id": "v120",
      "parent": "v88",
      "direction": "tighten",
      "generation": 15
    }
  ],
  "ledger": [
    {"t":"2026-10-03T20:23:51.126Z","event":"reject","variant":"v94","direction":"emphasize-weakest-kr","s":null,"decision":"reject","fitness":0.6520293641285502},
    {"t":"2026-10-03T20:23:51.126Z","event":"reject","variant":"v95","direction":"tighten","s":null,"decision":"reject","fitness":0.6439441601857132},
    {"t":"2026-10-03T20:23:51.127Z","event":"reject","variant":"v96","direction":"add-example","s":null,"decision":"reject","fitness":0.6438240474467677},
    {"t":"2026-10-03T20:23:51.127Z","event":"propose","variant":"v97","direction":"add-example","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.127Z","event":"propose","variant":"v98","direction":"add-example","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.127Z","event":"reject","variant":"v99","direction":"reorder","s":null,"decision":"reject","fitness":0.6438240474467677},
    {"t":"2026-10-03T20:23:51.127Z","event":"reject","variant":"v97","direction":"add-example","s":null,"decision":"reject","fitness":0.6466825113699703},
    {"t":"2026-10-03T20:23:51.128Z","event":"reject","variant":"v98","direction":"add-example","s":null,"decision":"reject","fitness":0.6512035790895015},
    {"t":"2026-10-03T20:23:51.128Z","event":"propose","variant":"v100","direction":"prune","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.128Z","event":"propose","variant":"v101","direction":"emphasize-weakest-kr","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.128Z","event":"propose","variant":"v102","direction":"emphasize-weakest-kr","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.128Z","event":"reject","variant":"v100","direction":"prune","s":null,"decision":"reject","fitness":0.6512078356774467},
    {"t":"2026-10-03T20:23:51.129Z","event":"reject","variant":"v101","direction":"emphasize-weakest-kr","s":null,"decision":"reject","fitness":0.6458368213654477},
    {"t":"2026-10-03T20:23:51.130Z","event":"reject","variant":"v102","direction":"emphasize-weakest-kr","s":null,"decision":"reject","fitness":0.627979660364941},
    {"t":"2026-10-03T20:23:51.130Z","event":"propose","variant":"v103","direction":"reorder","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.130Z","event":"propose","variant":"v104","direction":"emphasize-weakest-kr","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.130Z","event":"propose","variant":"v105","direction":"reorder","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.131Z","event":"reject","variant":"v104","direction":"emphasize-weakest-kr","s":null,"decision":"reject","fitness":0.6425688866957622},
    {"t":"2026-10-03T20:23:51.131Z","event":"reject","variant":"v105","direction":"reorder","s":null,"decision":"reject","fitness":0.6373025465780262},
    {"t":"2026-10-03T20:23:51.132Z","event":"reject","variant":"v103","direction":"reorder","s":null,"decision":"reject","fitness":0.6365413416518353},
    {"t":"2026-10-03T20:23:51.132Z","event":"propose","variant":"v106","direction":"add-example","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.132Z","event":"propose","variant":"v107","direction":"add-example","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.132Z","event":"propose","variant":"v108","direction":"reorder","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.132Z","event":"reject","variant":"v106","direction":"add-example","s":null,"decision":"reject","fitness":0.6346643904156101},
    {"t":"2026-10-03T20:23:51.133Z","event":"reject","variant":"v108","direction":"reorder","s":null,"decision":"reject","fitness":0.6392552349591598},
    {"t":"2026-10-03T20:23:51.133Z","event":"reject","variant":"v107","direction":"add-example","s":null,"decision":"reject","fitness":0.6499623191539247},
    {"t":"2026-10-03T20:23:51.134Z","event":"propose","variant":"v109","direction":"explore","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.134Z","event":"propose","variant":"v110","direction":"reorder","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.134Z","event":"propose","variant":"v111","direction":"prune","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.135Z","event":"reject","variant":"v110","direction":"reorder","s":null,"decision":"reject","fitness":0.6475799983748709},
    {"t":"2026-10-03T20:23:51.136Z","event":"reject","variant":"v109","direction":"explore","s":null,"decision":"reject","fitness":0.6482736137896145},
    {"t":"2026-10-03T20:23:51.136Z","event":"reject","variant":"v111","direction":"prune","s":null,"decision":"reject","fitness":0.6481647795950469},
    {"t":"2026-10-03T20:23:51.136Z","event":"propose","variant":"v112","direction":"emphasize-weakest-kr","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.136Z","event":"propose","variant":"v113","direction":"tighten","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.136Z","event":"propose","variant":"v114","direction":"emphasize-weakest-kr","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.137Z","event":"reject","variant":"v113","direction":"tighten","s":null,"decision":"reject","fitness":0.6449799291120413},
    {"t":"2026-10-03T20:23:51.137Z","event":"reject","variant":"v112","direction":"emphasize-weakest-kr","s":null,"decision":"reject","fitness":0.6490772212601349},
    {"t":"2026-10-03T20:23:51.138Z","event":"reject","variant":"v114","direction":"emphasize-weakest-kr","s":null,"decision":"reject","fitness":0.64643596073202},
    {"t":"2026-10-03T20:23:51.138Z","event":"propose","variant":"v115","direction":"explore","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.138Z","event":"propose","variant":"v116","direction":"prune","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.138Z","event":"reject","variant":"v117","direction":"reorder","s":null,"decision":"reject","fitness":0.64643596073202},
    {"t":"2026-10-03T20:23:51.139Z","event":"reject","variant":"v115","direction":"explore","s":null,"decision":"reject","fitness":0.6452874961604277},
    {"t":"2026-10-03T20:23:51.139Z","event":"reject","variant":"v116","direction":"prune","s":null,"decision":"reject","fitness":0.6426935572176797},
    {"t":"2026-10-03T20:23:51.139Z","event":"propose","variant":"v118","direction":"add-example","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.139Z","event":"propose","variant":"v119","direction":"prune","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.139Z","event":"propose","variant":"v120","direction":"tighten","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.140Z","event":"promote","variant":"v120","direction":"tighten","s":null,"decision":"promote","fitness":0.6529444391477058},
    {"t":"2026-10-03T20:23:51.141Z","event":"propose","variant":"v121","direction":"tighten","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.141Z","event":"propose","variant":"v122","direction":"tighten","s":null,"decision":null,"fitness":null},
    {"t":"2026-10-03T20:23:51.141Z","event":"propose","variant":"v123","direction":"emphasize-weakest-kr","s":null,"decision":null,"fitness":null}
  ],
  "envId": "sim",
  "policy": "# Coding habits\n\nStrength 0–1: how often the agent does it.\n\n- Write a failing test first (0.00)\n- Read the whole file before editing (0.80)\n- Reuse existing helpers (0.86)\n- Answer in one pass, skip re-checks (0.65)\n- Keep diffs small (0.90)\n- Run the full test suite after each change (0.00)\n"
}
```
  1. cli export
  2. push to GitHub
  3. npx skills add you/your-brain

It keeps learning from where you left off.

learnabolicp. 10 / 13

§ 11 · coming next

More worlds to learn in.

envs/touchdown

coming soon

Touchdown

A model that never sees the game writes a lander autopilot, and learns from scores alone.

Follow on GitHub →
envs/autoresearch

coming soon

Ratcheted autoresearch

Karpathy's overnight loop, with noise-aware keeps and a learned research taste.

Follow on GitHub →
learnabolicp. 11 / 13

§ 12 · inspirations and credits

Standing on good shoulders.

Built at Sundai X Copenhagen, October 2026. Theme: reinforcement learning for agents.

Acknowledgements: thanks to Connie for brainstorming the idea together at Sundai X Copenhagen, 3 October 2026.

learnabolicp. 12 / 13

§ 13 · learnabolic

GitHub · MIT · Made with care by Age van der Mei.