Skip to main content

Presets for guiding agentic AI workflows

Project description

Sheave 🧭

CI License: MIT-aNOAI Discord

Presets for guiding agentic AI workflows.
Because tasks shouldn't get lost in translation.

📘 Roadmap · 📝 Release Notes

[!NOTE] Heads up: the AI cooked dinner. It's edible, but watch your step. Detailed bug reports welcome.

🚀 Quick Start

Sheave provides preset rules, workflows, and commands for AI-powered IDE integrations like Cursor, Claude Desktop, and similar tools. These presets can be selectively enabled, similar to how you configure linter rules.

Installation

# Using poetry
poetry add sheave

# Using pip
pip install sheave

Basic Usage

# Enable specific presets (coming soon)
sheave enable --rules code-quality --workflows testing

# List available presets
sheave list

# Apply presets to your project
sheave sync

🎯 What is Sheave?

Sheave offers a curated collection of AI guidance presets that you can selectively enable:

  • Preset Rules: Pre-configured prompt rules that get added to each AI interaction

    • Code quality standards
    • Testing best practices
    • Documentation guidelines
    • Security considerations
  • Preset Workflows: Common workflows you can point an AI assistant to

    • Setting up new features
    • Refactoring patterns
    • Debugging strategies
    • Code review checklists
  • Preset Commands: Ready-to-use commands for common development tasks

    • Generate test files
    • Create documentation
    • Run code quality checks
    • Format and lint code

All of these leverage functionality that already exists in your IDE — Sheave just provides a well-organized, selective set of presets you can opt into, similar to how ruff lets you choose which linting rules to enable.

✨ Features

  • 🎯 Selective presets — Choose only the rules, workflows, and commands you need
  • 🔌 IDE integration — Works with Cursor, Claude Desktop, and similar tools
  • 📦 Zero dependencies — Lightweight and focused
  • 🧩 Modular — Enable or disable presets independently
  • 🔧 Configurable — Customize presets to match your project's needs

⚖️ License

You're free to use, copy, and modify the script under the standard MIT terms.
The additional rider simply requests that this project not be used to train or fine-tune AI/ML systems until the author deems fair compensation frameworks exist.
Normal use, packaging, and redistribution for human developers are unaffected.

🪶 Summary

Use it. Hack it. Ship it.
It's MIT-licensed, minimal, and meant to stay out of your way — just with one polite request: don't feed it to the AIs (yet).


AI was used to help draft language, formatting, and code — plus we just love em dashes.

😐 Apathetic Tools © MIT-aNOAI

Project details


Download files

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

Source Distribution

sheave-0.2.0.tar.gz (16.3 kB view details)

Uploaded Source

Built Distribution

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

sheave-0.2.0-py3-none-any.whl (14.4 kB view details)

Uploaded Python 3

File details

Details for the file sheave-0.2.0.tar.gz.

File metadata

  • Download URL: sheave-0.2.0.tar.gz
  • Upload date:
  • Size: 16.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for sheave-0.2.0.tar.gz
Algorithm Hash digest
SHA256 99b8049afb0720b9d7a59fa9f07c9462cc0a61eab13911adf8e08c751d69d04e
MD5 de7ee8fddf9167ff88cff79f99cf189e
BLAKE2b-256 eb38df65f90e79a1635f03b3ed07fd031e5e569f5af581838c2dd941e03a9ac4

See more details on using hashes here.

Provenance

The following attestation bundles were made for sheave-0.2.0.tar.gz:

Publisher: publish_pypi.yml on apathetic-tools/sheave

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file sheave-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: sheave-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 14.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for sheave-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d6a2683bf81932e60b9a5b86c536b70d63740fdf13feee3bfcce3c08106bc8af
MD5 c1382bbd2fa800a5b03e8a1a7ef1ed1e
BLAKE2b-256 4f878af54f3e843b01e2135df2d2c9c0c37266d0ee34e06da8f27fd94a290191

See more details on using hashes here.

Provenance

The following attestation bundles were made for sheave-0.2.0-py3-none-any.whl:

Publisher: publish_pypi.yml on apathetic-tools/sheave

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page