This release is a pre-release and may not be stable for production use.
ubrain: Untrained Brain
Never trained, always learning.
A brain you can run on a laptop. It learns from experience by local plasticity, as synapses do: one-shot memories, values learned from reward, a cerebellum that learns its body. No pre-training, no gradient descent, no dataset. Plug in any trained AI model (CLIP, a language model) as its senses, and any body (a simulated humanoid robot, a Gymnasium game) as its interface.
Every behaviour of the brain follows a law written down before it was measured, and ubrain can tell you, before you run it, what the brain will do with your model's codes: a certificate.
Five minutes to a learning brain
git clone https://github.com/untrained-brain/ubrain
cd ubrain
uv run examples/01_whole_brain.py # the whole brain learns which action each picture asks for
uv run examples/03_keep.py # save it, load it, and it continues exactly
(uv installs Python and the dependencies for you; numpy is the only one.)
On Windows, clone with long paths on, or the robot's kitchen world stops the checkout half-way ("Filename too long"):
git clone -c core.longpaths=true https://github.com/untrained-brain/ubrain
(Prefer the clone to the ZIP download: Windows' own unzip has the same 260-character path limit.)
Every example uses the whole brain, Brain(), and has the same shape: what it shows, the
question, a twin (the same run with one thing changed), and a check -- its last line is
CHECK PASS or CHECK FAIL, and its exit code says the same.
| example | the question | needs |
|---|---|---|
00_check_setup.py |
is this computer ready for the robot examples? (2 minutes) | the body |
01_whole_brain.py |
does the whole brain learn which action each picture asks for? (twin: unrelated pictures) | nothing |
02_ask.py |
what does the brain say about itself: describe, read, datasheet, health? | nothing |
03_keep.py |
does a saved and loaded brain choose exactly what the original would? | nothing |
04_g1_brace.py |
does the whole brain keep the G1 up when a tone warns of a push? (twin: no tone) | the body |
05_g1_choose.py |
does it learn which way to turn from a picture? (twin: unrelated pictures) | the body |
06_g1_keep.py |
trained, saved and loaded: does the demo brain stay up where a fresh one falls? | the body |
07_g1_lead.py |
how long a warning can the cerebellum use? (a prediction written first, and it failed) | the body |
08_g1_vision.py |
what does the brain call new, seeing through the head camera with CLIP? (twin: covered camera) | the body, --extra vision, the CLIP weights |
"The body" means the robot, set up once: it ships in this repository, in bodies/mujoco
(its own environment: MuJoCo, the G1, the photo gallery); cd bodies/mujoco && uv sync.
The robot examples take --viewer to watch in real time. "The CLIP weights" are fetched
once per machine (about 600 MB).
Use it in your own code
ubrain is on PyPI as compiled wheels (Windows, macOS, Linux; Python 3.11-3.13). Every version is a pre-release until 1.0, so name the version (or allow pre-releases):
uv add "ubrain==0.46.0.dev3"
# or with pip: pip install "ubrain==0.46.0.dev3" (or: pip install --pre ubrain)
The same wheels are in this repository's wheels/ folder, for a machine without PyPI access
(pip install ubrain==0.46.0.dev3 --find-links /path/to/ubrain/wheels). The robot, the
examples and the docs are in the repository: https://github.com/untrained-brain/ubrain.
The whole brain needs no wiring: choose a variant, attach streams by port class, tick it (a
preview: the whole is not yet certified as a whole; examples/01_whole_brain.py shows what it
does and the law beside it):
from ubrain import Brain, GaussianCodes
brain = Brain(variant="small")
brain.attach("sense", "vision", codec=GaussianCodes(dim=64, seed=1)) # any frozen model as the codec
brain.attach("reward")
brain.attach("action", n=4)
action = brain.tick({"sense.vision": 2, "reward": None})["action"]
A robot: ubrain.bodies.g1.G1(hello).attach(brain) adds the body's streams (body, cue,
goal, command); see examples/04_g1_brace.py.
Extras, each installed only when you ask for it: ubrain[vision] (CLIP as a sense: torch,
transformers), ubrain[video] (MP4 recording), ubrain[plot] (matplotlib).
The manual
- Quickstart: install, run, what you are looking at
- Using ubrain in your own code: install from the wheels, write your own
- Concepts: regions, wiring, bodies, codecs and certificates
- The examples (
examples/): each one short, meant to be copied, on the whole brain, ending with its check
Three layers
| layer | what | examples |
|---|---|---|
| codecs (plug-in) | frozen AI models that turn the world into codes | CLIP (ubrain[vision]) |
| the brain | Brain(): every region, wired once, stepped one tick at a time; numpy only |
hippocampus, cortex, prefrontal cortex, striatum, cerebellum, salience, thalamus, neuromodulators |
| bodies (plug-in) | anything that sends senses and takes actions | the MuJoCo G1 (over a small protocol), a Gymnasium game with discrete states (ubrain.bodies.gym) |
from ubrain import Brain, GaussianCodes
brain = Brain(variant="small")
brain.attach("sense", "vision", codec=GaussianCodes(dim=64, seed=1))
brain.attach("reward"); brain.attach("action", n=4)
action = brain.tick({"sense.vision": s, "reward": r})["action"]
Status
Pre-release, 0.46.0.dev3: the whole brain, Brain(), with seventeen regions. The cerebellum (a forward
model, a timed brace, walking adaptation); the striatum (on an index, or on a situation code
conditioned by a goal); the hippocampus (an episode, and a
store that acts, keyed through the dentate gyrus) and the hand-over from it to the striatum; the cortex's slow store; the
prefrontal cortex's working memory (active and silent); the salience gate and the mode
controller; the thalamus; and three neuromodulators (acetylcholine, noradrenaline,
serotonin). The regions are certified copies from a research engine in which every law is
written down before it is measured; ubrain never changes a region's code by hand. How the
engine is built is the subject of The Untrained Brain Series, Volume 2: Building the
Brain Engine (in preparation).
Copyright 2026 Hong Jeong. The examples, documentation and profiles are under the
Apache License 2.0 (LICENSE); the ubrain package is distributed compiled, under
LICENSE-BINARY: free for any use, commercial included; you may ship it unmodified inside
what you build, but not republish it on its own, modify it or reverse-engineer it.
The robot body in bodies/mujoco is Apache-2.0, with third-party parts under their own
licences (its NOTICE).
Metadata
Release files for ubrain 0.46.0.dev3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
Total release size: 84.8 MB
Release files / ubrain-0.46.0.dev3-cp313-cp313-win_amd64.whl
| Download URL | ubrain-0.46.0.dev3-cp313-cp313-win_amd64.whl |
|---|---|
| Size | 2.5 MB |
| Tags | CPython 3.13 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
db60fc351cc711663df1a837950c7a02ce893f49a3936dbd44bef8228be609b7
|
|
BLAKE2b-256 checksum How to use checksums |
0047007b448d84277f685625cb9e4ae68f470135c67d450216a11ba6a64cb6e5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / ubrain-0.46.0.dev3-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl
| Download URL | ubrain-0.46.0.dev3-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 19.7 MB |
| Tags | CPython 3.13 Linux glibc 2.17+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
46b9d7bc39728cc8bec07b15f615e2db1a2a133dcd0d8ab533ac4b2b20bbf345
|
|
BLAKE2b-256 checksum How to use checksums |
7f23536a490fc9515f6d2ddfb60fa21bab25a12f0e8569218e5ec28a56722c39
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / ubrain-0.46.0.dev3-cp313-cp313-macosx_11_0_arm64.whl
| Download URL | ubrain-0.46.0.dev3-cp313-cp313-macosx_11_0_arm64.whl |
|---|---|
| Size | 2.9 MB |
| Tags | CPython 3.13 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
6b1bb55cffdf4942a8421cf8b8a70946a89b2ee22101d30ef5e1158839c978d6
|
|
BLAKE2b-256 checksum How to use checksums |
9406817423d68290062dca233c2c5bbd64fd9dc3802b0414c5137fc7d46eb0a4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / ubrain-0.46.0.dev3-cp313-cp313-macosx_10_13_x86_64.whl
| Download URL | ubrain-0.46.0.dev3-cp313-cp313-macosx_10_13_x86_64.whl |
|---|---|
| Size | 3.0 MB |
| Tags | CPython 3.13 macOS 10.13+ x86-64 |
|
SHA-256 checksum How to use checksums |
e1c079a88f65f76764a64d73a15610115e18da579a73c4381cd32ecc19ad8027
|
|
BLAKE2b-256 checksum How to use checksums |
d1ddd42f174e0b844bec9b08ac8fe6a3b4cd2a7f035b27a5cb6417319771dc7b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / ubrain-0.46.0.dev3-cp312-cp312-win_amd64.whl
| Download URL | ubrain-0.46.0.dev3-cp312-cp312-win_amd64.whl |
|---|---|
| Size | 2.5 MB |
| Tags | CPython 3.12 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
0a08ca43886e466d481fa006517f247b01bd0f068f29d47727070a1f4d03f87e
|
|
BLAKE2b-256 checksum How to use checksums |
30984f4c30063aef69e02b62dd066eefab65005a367ecfb2af812ffabdd62a55
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / ubrain-0.46.0.dev3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl
| Download URL | ubrain-0.46.0.dev3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 20.0 MB |
| Tags | CPython 3.12 Linux glibc 2.17+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
c4cbabe62fc6425e9876714524f5aa9de7b01bff96102bb5b34c4d1c9e79304b
|
|
BLAKE2b-256 checksum How to use checksums |
0d9e35ecdd5768efac3004870ed916e8aae20aefabdf1833e25f1be98f20686f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / ubrain-0.46.0.dev3-cp312-cp312-macosx_11_0_arm64.whl
| Download URL | ubrain-0.46.0.dev3-cp312-cp312-macosx_11_0_arm64.whl |
|---|---|
| Size | 3.0 MB |
| Tags | CPython 3.12 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
14a7afaf046238ab29619f92a70bd1a5a8a4f0a637e6fdadb3a010c06f8a6c36
|
|
BLAKE2b-256 checksum How to use checksums |
db14bf9b58299e5ce5e62021b2c874966bd77cfd4810f086e3b10561ef2f4a70
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / ubrain-0.46.0.dev3-cp312-cp312-macosx_10_13_x86_64.whl
| Download URL | ubrain-0.46.0.dev3-cp312-cp312-macosx_10_13_x86_64.whl |
|---|---|
| Size | 3.0 MB |
| Tags | CPython 3.12 macOS 10.13+ x86-64 |
|
SHA-256 checksum How to use checksums |
2597017e2208239615694a546380c943be70ab21e08a0b57fc3e395714273174
|
|
BLAKE2b-256 checksum How to use checksums |
f16e58b1e0e11da7b71bd075a485397966d6b436da37838d6ece98ab14ee02e6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / ubrain-0.46.0.dev3-cp311-cp311-win_amd64.whl
| Download URL | ubrain-0.46.0.dev3-cp311-cp311-win_amd64.whl |
|---|---|
| Size | 2.6 MB |
| Tags | CPython 3.11 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
a8b75202063011edf31f9b544580e8ae62366ed595813c09eaa39ea66a90f9b3
|
|
BLAKE2b-256 checksum How to use checksums |
0c3c9a7b492fa0f560ef03aba14542fe2ef97264c2ab966ad17914036bc776b1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / ubrain-0.46.0.dev3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl
| Download URL | ubrain-0.46.0.dev3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 19.7 MB |
| Tags | CPython 3.11 Linux glibc 2.17+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
d88c7d7f5d4bfd7b36f5cbdd891d1af672604e2618623d6252862500f7693a95
|
|
BLAKE2b-256 checksum How to use checksums |
524a9b732c0012ed9f73209bac15cb479f2d42bd0d202fc4925948b113c5f406
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / ubrain-0.46.0.dev3-cp311-cp311-macosx_11_0_arm64.whl
| Download URL | ubrain-0.46.0.dev3-cp311-cp311-macosx_11_0_arm64.whl |
|---|---|
| Size | 2.9 MB |
| Tags | CPython 3.11 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
c61d014b28f61ec9ae05283f8335369299571119f0a9173881638cad3d57e360
|
|
BLAKE2b-256 checksum How to use checksums |
87144a8e4aece0bea0d0e299898f5efe5a0a06af37894a098b859cd1869cbf39
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / ubrain-0.46.0.dev3-cp311-cp311-macosx_10_9_x86_64.whl
| Download URL | ubrain-0.46.0.dev3-cp311-cp311-macosx_10_9_x86_64.whl |
|---|---|
| Size | 3.0 MB |
| Tags | CPython 3.11 macOS 10.9+ x86-64 |
|
SHA-256 checksum How to use checksums |
e72e81dc3fd0157772935586aff51a675bdc2e16692a66f10266224aadbecaf7
|
|
BLAKE2b-256 checksum How to use checksums |
531abc67f39c19f76d4fce0e009953c590a34ed738d55541bd7e585783352966
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Security for ubrain 0.46.0.dev3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.