SHarLe (Spec-Harness-Learning): a framework for spec-driven harness-based learning with LLMs.
Project description
SHarLe — Spec-Harness-Learning
SHarLe (Spec-Harness-Learning) is a Python framework for spec-driven, harness-based learning with large language models.
🚧 Early development — APIs are unstable.
Install
pip install sharle
Quickstart
import sharle
print(sharle.__version__)
Development
This project uses uv for environment management.
# create env and install with dev extras
uv sync --extra dev
# run tests
uv run pytest
# lint & format
uv run ruff check .
uv run ruff format .
# type-check
uv run mypy
Building & publishing
uv run python -m build
uv run twine check dist/*
uv run twine upload dist/*
License
MIT © Maxime Rivest
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
sharle-0.0.1.tar.gz
(3.0 kB
view details)
Built Distribution
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