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
1 maintainer
Metadata
1 maintainer
Release files for sharle 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| sharle-0.0.1.tar.gz | 3.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| sharle-0.0.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 6.1 kB
