Thank you for interest in contributing to Quantiles Open source!
Quantiles open source projects provide local-first evaluation infrastructure for AI systems. We welcome contributions that improve reliability, reproducibility, developer ergonomics, agent workflows, documentation, and benchmark and evaluation support.
Before opening a pull request, please:
- Search existing issues and pull requests to avoid duplicate work.
- Open an issue for large changes, new benchmark integrations, schema changes, or API changes.
- Keep changes focused and reviewable.
- Update tests and documentation when behavior changes.
- If you use one, make sure your coding agent follows the instructions in
AGENTS.md.
- Keep each pull request focused on one clear problem or improvement.
- Add or update tests for new behavior, changed behavior, bug fixes, and regressions.
- Update documentation whenever CLI behavior, SDK APIs, workflows, benchmarks, schemas, or setup steps change.
- Use clear examples, commands, inputs, and expected outputs so changes are reproducible.
- Avoid unrelated refactors, formatting-only churn, generated files, or broad changes that make review harder.
Clone the repository:
git clone https://github.com/quantiles-evals/quantiles.git
cd quantilesFor the ./cli directory, ensure you have Rust installed and use the mise.toml file in that directory to run common build/lint/check/test commands. For the ./python directory, use the uv tool for similar commands. The typescript/ directory holds the yet-unreleased, unsupported TypeScript SDK.
Please do not report security vulnerabilities through public GitHub issues. Follow the reporting guidance in SECURITY.md.
By participating in this project, you agree to follow our CODE_OF_CONDUCT.md
By contributing, you agree that your contributions will be licensed under the Apache License 2.0.