{"id":31021359,"url":"https://github.com/sisl/astra-rl","last_synced_at":"2025-09-13T11:20:49.703Z","repository":{"id":302389467,"uuid":"967696174","full_name":"sisl/astra-rl","owner":"sisl","description":"The Adaptive Stress Testing for Robust AI (ASTRA) toolbox provides tooling to support model developers and testing in the full life cycle of making more robust AI Systems through the application of adaptive stress testing and adversarial training.","archived":false,"fork":false,"pushed_at":"2025-09-12T06:31:08.000Z","size":1740,"stargazers_count":5,"open_issues_count":3,"forks_count":0,"subscribers_count":7,"default_branch":"main","last_synced_at":"2025-09-12T08:35:34.854Z","etag":null,"topics":["ai-tools","aisafe","llms","robust-ai","stress-testing"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sisl.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/contributing.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-04-16T21:21:47.000Z","updated_at":"2025-09-12T06:06:51.000Z","dependencies_parsed_at":"2025-07-18T03:42:31.980Z","dependency_job_id":"479bccdd-da80-465a-ad5e-35fd280d86b9","html_url":"https://github.com/sisl/astra-rl","commit_stats":null,"previous_names":["sisl/astra-toolbox","sisl/astra-rl"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/sisl/astra-rl","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sisl%2Fastra-rl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sisl%2Fastra-rl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sisl%2Fastra-rl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sisl%2Fastra-rl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sisl","download_url":"https://codeload.github.com/sisl/astra-rl/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sisl%2Fastra-rl/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274955739,"owners_count":25380669,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-13T02:00:10.085Z","response_time":70,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-tools","aisafe","llms","robust-ai","stress-testing"],"created_at":"2025-09-13T11:20:48.341Z","updated_at":"2025-09-13T11:20:49.686Z","avatar_url":"https://github.com/sisl.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003c!-- \u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/duncaneddy/brahe/\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/duncaneddy/brahe/main/docs/pages/assets/logo-gold.png\" alt=\"Brahe\"\u003e\u003c/a\u003e\n\u003c/p\u003e --\u003e\n\u003cp align=\"center\"\u003e\n    \u003cem\u003eASTRA - Adaptive Stress Testing for Robust AI\u003c/em\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n\u003ca href=\"https://github.com/sisl/astra-rl/actions/workflows/ci.yml\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://github.com/sisl/astra-rl/actions/workflows/ci.yml/badge.svg\" alt=\"Test\"\u003e\n\u003c/a\u003e\n\u003ca href='https://coveralls.io/github/sisl/astra-rl?branch=main'\u003e\u003cimg src='https://coveralls.io/repos/github/sisl/astra-rl/badge.svg?branch=main' alt='Coverage Status' /\u003e\u003c/a\u003e\n\u003ca href=\"https://sisl.github.io/astra-rl/index.html\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/docs-latest-blue.svg\" alt=\"Docs\"\u003e\n\u003c/a\u003e\n\u003ca href=\"https://github.com/sisl/astra-rl/blob/main/LICENSE\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/License-MIT-green.svg\", alt=\"License\"\u003e\n\u003c/a\u003e\n\u003c/p\u003e\n\n----\n\n# ASTRA-RL Toolbox\n\nASTRA-RL is a python toolbox for training and evaluating language models and generative AI systems that\nuse textual inputs. It provides a set of tools for training, evaluating, and analyzing\nlanguage models, with a focus on applying reinforcement learning based refinement techniques\nto improve evaluator model performance.\n\n## Installation\n\nTo install the ASTRA-RL toolbox, you can use pip. The package is available on PyPI, so you can install it directly from there.\n\n```bash\npip install astra-rl\n```\n\nYou can then import the library in your Python code:\n\n```python\nimport astra_rl\n# or\nimport astra_rl as astral\n```\n\n## Development\n\nThis section provides instructions for setting up the development environment and running tests.\n\nTo start, we _STRONGLY_ recommend using [uv](https://docs.astral.sh/uv/) to manage your Python environment. This will ensure that you have the correct dependencies and versions installed.\n\n### Setting Up the Development Environment\n\n1. Clone the repository:\n\n   ```bash\n   git clone https://github.com/sisl/astra-rl.git\n   cd astra-rl\n   ```\n\n2. Sync package dependencies:\n\n   ```bash\n   uv sync --dev\n   ```\n\n   This will create a `.venv` directory in the project root with all the necessary dependencies installed.\n   \n3. Install pre-commit hooks:\n\n   ```bash\n   uv run pre-commit install\n   ```\n   \n   This will ensure that the linter (`ruff`), formatter (`ruff`), and type checker (`mypy`) is happy with your code every time you commit.\n   \n### Running Tests\n\nAssuming you've set up your environment using `uv`, you can run the tests using the following command:\n\n```bash\npytest\n```\n\nor \n\n```bash\nuv run pytest\n```\n\nTo generate local coverage reports, you can use:\n\n```bash\nuv run coverage run -m pytest\nuv run coverage report # Generate CLI report\nuv run coverage html   # Generate HTML report\n```\n\n#### Running Tests with GPU\n\nSome tests may require a GPU to run. You can enable GPU tests by passing the `--gpu` option:\n\n```bash\nuv run pytest --gpu\n```\n\nThese tests will be _skipped_ by default unless you specify the `--gpu` option.\n\n### Generating Documentation\n\nTo generate the documentation, you can use the following command:\n\n```bash\nuv run mkdocs serve\n```\n\nThis will build the documentation and start a local server. You can then view the documentation in your web browser.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsisl%2Fastra-rl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsisl%2Fastra-rl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsisl%2Fastra-rl/lists"}