entroly-core
Rust core for Entroly, the information-theoretic context optimization engine for AI coding agents.
Provides high-performance PyO3 bindings for:
- Knapsack optimizer - 0/1 DP context selection within token budget
- Shannon entropy scorer - boilerplate detection, information density
- SimHash deduplication - near-duplicate fragment detection
- Query analysis - TF-IDF vagueness scoring, heuristic refinement
- SAST scanner - security rules for common vulnerability classes
- LSH index - approximate nearest-neighbor semantic recall
- PRISM RL optimizer - online feedback-driven fragment weight learning
Install
python -m pip install --upgrade pip
python -m pip install --no-cache-dir -U "entroly-core>=1.0.50"
Prebuilt abi3 wheels are published for Linux, macOS, and Windows. One
wheel per platform covers Python 3.10+ including Python 3.14. If pip
tries to compile an old source distribution such as 0.2.0, upgrade pip
and retry with --no-cache-dir; the intended path is the prebuilt wheel,
not a local PyO3 build.
Usage
Usually used via the higher-level entroly package:
python -m pip install entroly
entroly # starts the MCP server
Or directly:
from entroly_core import ContextFragment, py_knapsack_optimize, py_shannon_entropy
License
Apache-2.0
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distributions
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file entroly_core-1.0.50-cp310-abi3-win_amd64.whl.
File metadata
- Download URL: entroly_core-1.0.50-cp310-abi3-win_amd64.whl
- Upload date:
- Size: 2.3 MB
- Tags: CPython 3.10+, Windows x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4fb275ef41312f701148bceb412a3674d3aa2c410dde9bbc1bc4ee5fd974d53c
|
|
| MD5 |
7888f60a10756272d60f6838e69b08a2
|
|
| BLAKE2b-256 |
8539a5451868f74567024dcaf93dee96d2429f05f4411130ff0db9ef3bcb031e
|
File details
Details for the file entroly_core-1.0.50-cp310-abi3-manylinux_2_28_aarch64.whl.
File metadata
- Download URL: entroly_core-1.0.50-cp310-abi3-manylinux_2_28_aarch64.whl
- Upload date:
- Size: 2.5 MB
- Tags: CPython 3.10+, manylinux: glibc 2.28+ ARM64
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f0979d5019f1137ea7d16ea93346a3b442d1d257205f5a381635ccc47897d82a
|
|
| MD5 |
46162e696646dfd98fb3db7e15fca0ec
|
|
| BLAKE2b-256 |
f18ceedf4b3074858a3ff3fdcc85d9a940062f1084a69dd07c15dbc894ec2ed9
|
File details
Details for the file entroly_core-1.0.50-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.
File metadata
- Download URL: entroly_core-1.0.50-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Upload date:
- Size: 2.6 MB
- Tags: CPython 3.10+, manylinux: glibc 2.17+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
46a3247c8779e147063e22e753f1800f2fce82e4d1531a02d03340a9f13bc4d8
|
|
| MD5 |
5bd23626805463b1717c89ba1e637129
|
|
| BLAKE2b-256 |
039d202d4d152c8c4ea389272225e293b61d4977cfa7da49905d2ec990855762
|
File details
Details for the file entroly_core-1.0.50-cp310-abi3-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl.
File metadata
- Download URL: entroly_core-1.0.50-cp310-abi3-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl
- Upload date:
- Size: 4.8 MB
- Tags: CPython 3.10+, macOS 10.12+ universal2 (ARM64, x86-64), macOS 10.12+ x86-64, macOS 11.0+ ARM64
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
965fa64ffc8b0d1dd5e73d97c88f1a911c7f99dbad0375810c5292ada09ba861
|
|
| MD5 |
0552cd5427095fab5d9c7f4fa407b0cb
|
|
| BLAKE2b-256 |
979cfdc0eb73d1f9a228088c7e1cbeb5e0a7dbe4148cae77a43ae12be58680eb
|
