Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

AI-Rulez

ai-rulez

PyPI version License

One source for the rules, skills and settings of every AI coding assistant. ai-rulez keeps them in a single .ai-rulez/ directory and generates the native files of 52 tools (AGENTS.md, CLAUDE.md, .cursor/rules/, skills, MCP and settings files), then validates, locks, signs and publishes them.

Documentation: goldziher.github.io/ai-rulez

Install

Requires Python 3.11 or newer.

pipx install ai-rulez     # or: uv tool install ai-rulez, pip install ai-rulez

Or run it without installing:

uvx ai-rulez init acme

The package installs the ai-rulez command. Platform wheels (Linux and macOS on amd64 and arm64, Windows on amd64) carry the ai-rulez Go binary, so installing needs no access beyond PyPI. Where no wheel matches, pip installs the source distribution and the launcher downloads the binary from the GitHub release that matches the package version on the first run, verifies its SHA-256 checksum and caches it in ~/.cache/ai-rulez. Linux binaries need glibc; Alpine (musl) is not supported.

Quickstart

ai-rulez init acme
ai-rulez add rule testing --content '# Testing

- Every bug fix ships with a regression test.'
ai-rulez generate

Set the tools you use in .ai-rulez/config.toml with presets = ["claude", "cursor", "codex"]. Run ai-rulez generate --check in CI to catch drift. The Quick start covers the rest.

Other channels

Homebrew (brew install goldziher/tap/ai-rulez), npm (npm install -g ai-rulez) and Go (go install github.com/Goldziher/ai-rulez/v5/cmd/ai-rulez@latest). See Installation.

Documentation · Source · Issues · MIT license

Metadata

Release files for ai-rulez 5.13.0rc1

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

Built distributions (wheels)

Table of built distributions (wheels) for ai-rulez 5.13.0rc1
File Actions
ai_rulez-5.13.0rc1-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details for ai_rulez-5.13.0rc1-py3-none-win_amd64.whl
ai_rulez-5.13.0rc1-py3-none-manylinux_2_34_x86_64.whl Python 3 none Linux glibc 2.34+ x86-64 Details for ai_rulez-5.13.0rc1-py3-none-manylinux_2_34_x86_64.whl
ai_rulez-5.13.0rc1-py3-none-manylinux_2_34_aarch64.whl Python 3 none Linux glibc 2.34+ ARM64 Details for ai_rulez-5.13.0rc1-py3-none-manylinux_2_34_aarch64.whl
ai_rulez-5.13.0rc1-py3-none-macosx_14_0_x86_64.whl Python 3 none macOS 14.0+ x86-64 Details for ai_rulez-5.13.0rc1-py3-none-macosx_14_0_x86_64.whl
ai_rulez-5.13.0rc1-py3-none-macosx_14_0_arm64.whl Python 3 none macOS 14.0+ ARM64 Details for ai_rulez-5.13.0rc1-py3-none-macosx_14_0_arm64.whl

Total release size: 169.5 MB

Release files / ai_rulez-5.13.0rc1-py3-none-win_amd64.whl

Download URL ai_rulez-5.13.0rc1-py3-none-win_amd64.whl
Size 33.2 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
992df148577336ba0f78effef55cd00df8556ccd9fe429dc507cd465c353d2d5
BLAKE2b-256 checksum
How to use checksums
1809b78f7aa32bcddbb4674497c1c351cbf0da7de3a0991b882ae9a670803006
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 Nov 14, 2026.

Transparency log

Release files / ai_rulez-5.13.0rc1-py3-none-manylinux_2_34_x86_64.whl

Download URL ai_rulez-5.13.0rc1-py3-none-manylinux_2_34_x86_64.whl
Size 35.4 MB
Tags Linux glibc 2.34+ x86-64 Python 3
SHA-256 checksum
How to use checksums
d89e1887c608fbc555fda0eac71517ecdfd847e4e54104c97af6ffd8abb51b93
BLAKE2b-256 checksum
How to use checksums
7425d4d6fc0f62e9cc8e1446ed8e4a3d041635f68722984ab336339f08e46c1f
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 Nov 14, 2026.

Transparency log

Release files / ai_rulez-5.13.0rc1-py3-none-manylinux_2_34_aarch64.whl

Download URL ai_rulez-5.13.0rc1-py3-none-manylinux_2_34_aarch64.whl
Size 32.4 MB
Tags Linux glibc 2.34+ ARM64 Python 3
SHA-256 checksum
How to use checksums
d71b1e765e1b9ba3f627f59c256764b4d188e480dceed316653b6e3b83cc957c
BLAKE2b-256 checksum
How to use checksums
a5d20d83c6affc0e024e23ace43668e5bf7d3e5d9189d89fd4c647eb4239f111
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 Nov 14, 2026.

Transparency log

Release files / ai_rulez-5.13.0rc1-py3-none-macosx_14_0_x86_64.whl

Download URL ai_rulez-5.13.0rc1-py3-none-macosx_14_0_x86_64.whl
Size 35.8 MB
Tags Python 3 macOS 14.0+ x86-64
SHA-256 checksum
How to use checksums
3be24cd7bba76eedc963893a433925d4f504f5eee97d6e160b558a9521ed6aeb
BLAKE2b-256 checksum
How to use checksums
e77834f2107caab37ed15c6ec0ac85eea18833bdabf57ee7f31b482490bcdf91
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 Nov 14, 2026.

Transparency log

Release files / ai_rulez-5.13.0rc1-py3-none-macosx_14_0_arm64.whl

Download URL ai_rulez-5.13.0rc1-py3-none-macosx_14_0_arm64.whl
Size 32.8 MB
Tags Python 3 macOS 14.0+ ARM64
SHA-256 checksum
How to use checksums
16914af72481eab3d6f76c30e82af8e90d2eee71fde524fe2e783263a3b2be6c
BLAKE2b-256 checksum
How to use checksums
ffff23a2a02a2ad67ce5a34cd0f1757907b9110c8d27c49edd19614e39d3e79f
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 Nov 14, 2026.

Transparency log

Security for ai-rulez 5.13.0rc1

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 5 files in this release have been uploaded with provenance metadata.

Select from 5 files

Attestation for ai_rulez-5.13.0rc1-py3-none-win_amd64.whl

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 Nov 14, 2026.

Transparency log

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.

Release history Release notifications | RSS feed

5.13.1

This release
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