pymlkit
A small, dependency-free neural network library with a C core and a Python wrapper. Dense feed-forward networks, mini-batch SGD, binary weight import/export, and REINFORCE reinforcement learning (C API).
Python
pip install pymlkit # or, from a clone: pip install .
from pymlkit import Network, Activations, Losses
model = Network(2) # 2 inputs
model.add_dense(16, Activations.ReLU)
model.add_dense(1, Activations.Sigmoid)
model.set_loss(Losses.HalfMSE)
# data is a flat list: [x1a, x1b, x2a, x2b, ...] / [y1, y2, ...]
model.fit(train_x, train_y, lr=0.1, epochs=100, batch=16)
print(model.forward([0.1, 0.2])) # -> [0.93]
model.export("model.mlk") # model.load("model.mlk") to restore
| Method | Description |
|---|---|
Network(input_size) |
Create a network |
add_dense(n, activation) |
Append a dense layer (output layer last) |
set_loss(loss) |
Losses.HalfMSE or Losses.CrossEntropy |
fit(x, y, lr, epochs, batch, log_step) |
Mini-batch SGD |
forward(x) |
One sample in, list of outputs out |
backward(y) |
Accumulate gradients for one sample (custom loops) |
export(path) / load(path) |
Save / load weights; load returns False if the file is missing |
Activations: ReLU, Linear, Softmax, Sigmoid. Example:
python/examples/circle_classifier.py.
C
The same library, usable directly from C (MLKit.c / MLKit.h):
#include "MLKit.h"
Network* net = nn_network_create(2);
nn_add_layer_dense(net, 8, activation_reLU);
nn_add_layer_dense(net, 1, activation_sigmoid);
nn_network_set_loss(net, CrossEntropy);
nn_network_fit(net, x_train, 4, y_train, 0.1f, 2000, 4, 500);
float* out = nn_network_forward(net, sample);
nn_network_export(net, "model.mlk");
nn_network_destroy(net);
gcc -Ofast -o example example.c MLKit.c -lm # or: cmake -S . -B build && cmake --build build
Compile with -Ofast (MSVC: /O2 /fp:fast) for much faster training. The
CMake build and the PyPI wheels already do this.
Main functions: nn_network_create, nn_add_layer_dense, nn_network_set_loss,
nn_network_fit, nn_network_forward, nn_network_backward,
nn_apply_gradients, nn_network_test, nn_network_export,
nn_network_import_file, nn_network_destroy. Signatures are in MLKit.h.
Reinforcement learning (REINFORCE): rl_agent_create, rl_draw_action,
rl_remember, rl_policy_fit, rl_agent_destroy. See
examples/snake/ for a full Snake agent.
Notes
- Weights are stored as flat
float32arrays; the.mlkfile is a rawfloat32stream (bias, then weights, per neuron). - Loading a model does not check that the architecture matches.
- No shuffling between epochs. CPU only. A learning/prototyping library, not production-hardened.
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for pymlkit 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| pymlkit-0.1.1.tar.gz | 11.6 kB | With provenance | Details |
Built distributions (wheels)
| File | Reset | |||
|---|---|---|---|---|
| pymlkit-0.1.1-py3-none-win_amd64.whl | Python 3 | none | Windows x86-64 | Details |
| pymlkit-0.1.1-py3-none-win32.whl | Python 3 | none | Windows x86-32 | Details |
| pymlkit-0.1.1-py3-none-pyemscripten_2026_0_wasm32.whl | Python 3 | none | PyEmscripten 2026.0+ WebAssembly | Details |
| pymlkit-0.1.1-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl | Python 3 | none | Linux glibc 2.17+ x86-64 | Details |
| pymlkit-0.1.1-py3-none-macosx_11_0_arm64.whl | Python 3 | none | macOS 11.0+ ARM64 | Details |
| pymlkit-0.1.1-py3-none-macosx_10_13_x86_64.whl | Python 3 | none | macOS 10.13+ x86-64 | Details |
Total release size: 114.8 kB
Release files / pymlkit-0.1.1.tar.gz
| Download URL | pymlkit-0.1.1.tar.gz |
|---|---|
| Size | 11.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
62c6950dd6741c45c9f211cd6f7b6589d89c48cddcc9f52a0fa5215f4b84629e
|
|
BLAKE2b-256 checksum How to use checksums |
a4e20a69cb2a6a62de9b842b0e294f68663dd101ce034e7a85f59cfd587bc1f7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logRelease files / pymlkit-0.1.1-py3-none-win_amd64.whl
| Download URL | pymlkit-0.1.1-py3-none-win_amd64.whl |
|---|---|
| Size | 19.3 kB |
| Tags | Python 3 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
fc9f83e122605fc737a2a457f6dc8d21f121389184c98678cbae87c745278104
|
|
BLAKE2b-256 checksum How to use checksums |
c685ba99c31a08e5de9fdc466b28fbdb1011ba73d399268b19106a3b9c22f090
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logRelease files / pymlkit-0.1.1-py3-none-win32.whl
| Download URL | pymlkit-0.1.1-py3-none-win32.whl |
|---|---|
| Size | 16.3 kB |
| Tags | Python 3 Windows x86-32 |
|
SHA-256 checksum How to use checksums |
a1c292b492ed44d59a225beb3979f5c3fcfde271d13029d12ec68a78654752d6
|
|
BLAKE2b-256 checksum How to use checksums |
fbe43c4ab8e07540539cd70b59f9c7974b88ff2780230186c7c5e70416f3b613
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logRelease files / pymlkit-0.1.1-py3-none-pyemscripten_2026_0_wasm32.whl
| Download URL | pymlkit-0.1.1-py3-none-pyemscripten_2026_0_wasm32.whl |
|---|---|
| Size | 9.5 kB |
| Tags | PyEmscripten 2026.0+ WebAssembly Python 3 |
|
SHA-256 checksum How to use checksums |
a80f59207a9846eec264f0f54464fd90a78526546fa26488543287debf27198f
|
|
BLAKE2b-256 checksum How to use checksums |
4c1e59613596a4d97ec5a832f30e979869de7a65d156b357de66ad4269b9dc62
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logRelease files / pymlkit-0.1.1-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | pymlkit-0.1.1-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 16.9 kB |
| Tags | Linux glibc 2.17+ x86-64 Python 3 |
|
SHA-256 checksum How to use checksums |
b81363f35bf0d67f7278d7cf2c7ddb7928670b2369c76c159c9ea79aa22f89da
|
|
BLAKE2b-256 checksum How to use checksums |
fb55d30af3559e55a9d0543a13d220a1397268df98beb7db3330525ad32f26b3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logRelease files / pymlkit-0.1.1-py3-none-macosx_11_0_arm64.whl
| Download URL | pymlkit-0.1.1-py3-none-macosx_11_0_arm64.whl |
|---|---|
| Size | 19.9 kB |
| Tags | Python 3 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
7d3512cb6a40b4d6744017ee7f1c10931391d4a7815edb0e41451d174bdb3a82
|
|
BLAKE2b-256 checksum How to use checksums |
e5a317b042e4dc1c54461384ae522689f6c2fe6e31e6f67af37f33e3055e2639
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logRelease files / pymlkit-0.1.1-py3-none-macosx_10_13_x86_64.whl
| Download URL | pymlkit-0.1.1-py3-none-macosx_10_13_x86_64.whl |
|---|---|
| Size | 21.5 kB |
| Tags | Python 3 macOS 10.13+ x86-64 |
|
SHA-256 checksum How to use checksums |
9e3646be570544fe5ddc487dedb3d83390ea24eedc4ddc946b4e5746d464aaa5
|
|
BLAKE2b-256 checksum How to use checksums |
ad5469de54d28321c7fb7b2fc57573138eb4f9930c6a98c37cda0f466b5ed720
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logSecurity for pymlkit 0.1.1
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.
Full provenance
All 7 files in this release have been uploaded with provenance metadata.
Attestation for pymlkit-0.1.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logA 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.
