Skip to main content

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>=1.0.57"

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

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

entroly_core-1.0.57-cp310-abi3-win_amd64.whl (2.3 MB view details)

Uploaded CPython 3.10+Windows x86-64

entroly_core-1.0.57-cp310-abi3-manylinux_2_28_aarch64.whl (2.5 MB view details)

Uploaded CPython 3.10+manylinux: glibc 2.28+ ARM64

entroly_core-1.0.57-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.6 MB view details)

Uploaded CPython 3.10+manylinux: glibc 2.17+ x86-64

entroly_core-1.0.57-cp310-abi3-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl (4.8 MB view details)

Uploaded CPython 3.10+macOS 10.12+ universal2 (ARM64, x86-64)macOS 10.12+ x86-64macOS 11.0+ ARM64

File details

Details for the file entroly_core-1.0.57-cp310-abi3-win_amd64.whl.

File metadata

File hashes

Hashes for entroly_core-1.0.57-cp310-abi3-win_amd64.whl
Algorithm Hash digest
SHA256 da9940d6ef4db7c3d1e97b630a5fa61492760f4536cb8bcd94bea8ea07de2348
MD5 a463df8e9ff329b6acb0bc08f50d7b3f
BLAKE2b-256 7814c5f893fe6535b08cc797481872fbdfba8eea351a0ed49cc948b6e30c3275

See more details on using hashes here.

File details

Details for the file entroly_core-1.0.57-cp310-abi3-manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for entroly_core-1.0.57-cp310-abi3-manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 772ddae34f94dd8072170f04999524d1f402e810e4431e1c3d0efb4e2ba09953
MD5 8c0fdb8aa7467ec658e7c20a6fcba0f8
BLAKE2b-256 517be6b5155bb6624766f58e095861fc8a76527f9f3827c0a2d31e32dedbb46e

See more details on using hashes here.

File details

Details for the file entroly_core-1.0.57-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for entroly_core-1.0.57-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 52f662b9913359c33a47c8e0f49f470b6eca814e92d3b25e7669df5b47c271ae
MD5 aa103f87fcf44734880013d3ee0c09a2
BLAKE2b-256 88de17a1a83d0537afdf76dc0125ca5c44ee9487074cc8aab4a03569ab531b34

See more details on using hashes here.

File details

Details for the file entroly_core-1.0.57-cp310-abi3-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl.

File metadata

File hashes

Hashes for entroly_core-1.0.57-cp310-abi3-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl
Algorithm Hash digest
SHA256 f9933048f767243ea700000388c525ecb2be1be90c7a7c6709afce154cb471ff
MD5 6a3422cffdd5cee08c05cbcf132401f1
BLAKE2b-256 f9065e8cdcf737d16d0eb43c7efd18f79ad74bf815657d0bbcd2dbb69aec1980

See more details on using hashes here.

Release history Release notifications | RSS feed

1.0.78

4 files

1.0.77

4 files

1.0.76

4 files

1.0.75

4 files

1.0.74

4 files

1.0.72

4 files

1.0.70

4 files

1.0.69

4 files

1.0.68

4 files

1.0.67

4 files

1.0.66

4 files

1.0.65

4 files

1.0.64

4 files

1.0.63

4 files

1.0.62

4 files

1.0.61

4 files

1.0.60

4 files

1.0.59

4 files

1.0.58

4 files

This release

1.0.57 This release

4 files

1.0.54

4 files

1.0.53

4 files

1.0.52

4 files

1.0.51

4 files

1.0.50

4 files

1.0.49

4 files

1.0.48

4 files

1.0.47

4 files

1.0.46

4 files

1.0.44

4 files

1.0.42

4 files

1.0.41

4 files

1.0.40

4 files

1.0.39

4 files

1.0.38

4 files

1.0.37

4 files

1.0.25

4 files

1.0.24

4 files

1.0.23

4 files

1.0.22

4 files

1.0.21

4 files

1.0.20

4 files

1.0.19

4 files

1.0.18

4 files

1.0.17

4 files

1.0.16

4 files

1.0.15

4 files

1.0.14

4 files

1.0.13

4 files

1.0.12

4 files

1.0.11

4 files

1.0.6

4 files

1.0.5

4 files

1.0.4

4 files

1.0.3

4 files

0.19.13

4 files

0.19.12

4 files

0.19.11

4 files

0.19.10

4 files

0.19.9

4 files

0.19.8

4 files

0.19.7

4 files

0.19.5

4 files

0.19.4

4 files

0.19.3

4 files

0.19.2

6 files

0.19.1

6 files

0.19.0

6 files

0.18.0

6 files

0.17.0

6 files

0.16.0

4 files

0.15.1

4 files

0.15.0

4 files

0.14.1

4 files

0.9.0

4 files

0.8.6

4 files

0.8.1

4 files

0.7.0

4 files

0.6.4

4 files

0.6.2

4 files

0.6.1

4 files

0.6.0

4 files

0.3.3

2 files

0.3.2

2 files

0.3.1

2 files

0.3.0

3 files

0.2.0

2 files

0.1.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page