Overview

verifiers is our library for creating environments to train and evaluate LLMs.

verifiers is tightly integrated with the Environments Hub, as well as our training framework prime-rl and our Hosted Training platform.

Installation

We recommend installing the Prime CLI to interact with the environments.

# install uv
curl -LsSf https://astral.sh/uv/install.sh | sh
install the prime CLI
uv tool install prime

Further reading

• The docs contain short, human-written guides and overviews about the architecture.
• The AGENTS.md and skills are for coding agents and go into more details.

Contributing

We welcome community contributions. We use issues to track bugs and feature requests. If you hit a bug, a pain point, or have an idea for a feature, please open an issue.

Contributions are welcome via PR. Please follow these guidelines:

1. Install the pre-commit hooks so your code is formatted and type-checked.
2. Keep your PR in "Draft" until it is ready for review.
3. If your PR resolves an issue, link the issue in the PR description.
4. Run the tests for the areas you touched.

Pre-commit hooks

uv run pre-commit install

Tests

Unit tests run one component in isolation, with no network, and mirror the verifiers/v1 layout. Integration tests run real evals: they need PRIME_API_KEY and skip without it.

uv run pytest tests/unit -n auto                       # unit
uv run pytest tests/integration -n 8                   # integration
uv run pytest tests/integration/test_single_turn.py    # one behavior
uv run pytest tests/integration -m "docker and codex"  # one runtime and harness

Citation

Originally created by Will Brown (@willccbb).

@misc{brown_verifiers_2025,
  author       = {William Brown},
  title        = {{Verifiers}: Environments for LLM Reinforcement Learning},
  howpublished = {\url{https://github.com/PrimeIntellect-ai/verifiers}},
  year         = {2025}
}