Skip to main content
Yanked

This release has been yanked by its maintainers, and will be ignored by installers, except when explicitly specified.
Consider using release 2.0.1 instead.
Reason given by maintainers: Superseded by 2.0.1

knowlytix

Status: stable. The knowlytix family is live on PyPI at 1.0 — a stable release with a settled API. We'd love your feedback: email hello@knowlytix.ai or follow release notes on our blog.


What Knowlytix is

Knowlytix is a policy-governed harness for agentic AI in regulated industries. It sits between LLM generation and response delivery, turning probabilistic model outputs into decisions you can defend to a regulator: each claim is extracted, checked against your domain's rules, and recorded with a complete evidence trail.

Built for high-stakes domains — financial services regulatory review, clinical decision support, contract analysis, enterprise knowledge management — where "the model usually gets it right" isn't an answer.

More on the approach, benchmarks, and research: https://knowlytix.ai/platform.

Install

knowlytix is a meta-package — installing it pulls the whole family in one command:

pip install knowlytix

Requires Python ≥ 3.12. On an older interpreter pip reports "No matching distribution found for knowlytix" — that's the version gate, not a missing release. Check with python --version before installing.

That's equivalent to installing each of these directly:

Package Purpose
knowlytix-core Geometric memory core (geometry + LLM-layer foundations)
knowlytix-harness Policy-governance harness
knowlytix-knowledge Geometric expert system with LLM-augmented learning
knowlytix-benchmark Benchmarks and reference results
knowlytix-kal Knowledge Adapter Layer for GMS

All five packages are live on PyPI at 1.0 — install the meta-package and you'll have the full family in one environment. Pin a version if you need a reproducible build. Questions or feedback: hello@knowlytix.ai.

Optional extras:

pip install "knowlytix[compiler]"   # query compiler stack, for DynaQuery (needs a GPU to train)
pip install "knowlytix[viz]"        # plotly, for knowlytix.knowledge.viz

Uninstall

pip uninstall knowlytix only removes the meta-package itself — pip does not cascade to dependencies, so the five sibling packages stay installed. To remove the whole family, list them explicitly:

pip uninstall -y knowlytix knowlytix-core knowlytix-harness \
                 knowlytix-knowledge knowlytix-benchmark knowlytix-kal

Get in touch

License

Apache-2.0. See LICENSE.

Metadata

Release files for knowlytix 1.5.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for knowlytix 1.5.0
File Size Uploaded
knowlytix-1.5.0.tar.gz 7.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for knowlytix 1.5.0
File Interpreter ABI Platform
knowlytix-1.5.0-py3-none-any.whl Python 3 none any Details

Total release size: 14.4 kB

Release files / knowlytix-1.5.0.tar.gz

Download URL knowlytix-1.5.0.tar.gz
Size 7.4 kB
Tags Source
SHA-256 checksum
How to use checksums
ee350cbfbd072da225c7ad57bed1b17300108a8526e5ac985df37f94af047211
BLAKE2b-256 checksum
How to use checksums
0cb585b807409e04e5eb81b92c351abf51891de69019c23963185b8c4daeaf72
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 5, 2026.

Transparency log

Release files / knowlytix-1.5.0-py3-none-any.whl

Download URL knowlytix-1.5.0-py3-none-any.whl
Size 7.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
69b9b8937353db7f78598847d9bd98886f533f3f879148741f2c992e8b1e4d23
BLAKE2b-256 checksum
How to use checksums
8a2ab9e9b4d93c6e9fe5decbed5d1ef1bd031a8a71e4ed945269c0dc7fd77314
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 5, 2026.

Transparency log

Release history Release notifications | RSS feed

2.0.1

2 release files

This release

1.5.0 This release

2 release files

1.4.0

2 release files

1.3.0

2 release files

1.2.0

2 release files

1.1.0

2 release files

1.0.1

2 release files

1.0.0

2 release files

0.1.0

2 release files

0.0.2

2 release files

0.0.1

2 release 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