wisent-guard


Namewisent-guard JSON
Version 0.4.3 PyPI version JSON
download
home_pagehttps://github.com/yourusername/wisent-activation-guardrails
SummaryMonitor and guard against harmful content in language models
upload_time2025-07-21 23:03:59
maintainerNone
docs_urlNone
authorWisent Team
requires_python>=3.8
licenseNone
keywords nlp machine learning language models safety guardrails lm-evaluation-harness
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            # Wisent-Guard

<p align="center">
  <a href="https://github.com/wisent-ai/wisent-guard/stargazers">
    <img src="https://img.shields.io/github/stars/wisent-ai/wisent-guard" alt="stars" />
  </a>
  <a href="https://pypi.org/project/wisent-guard">
    <img src="https://static.pepy.tech/badge/wisent-guard" alt="PyPI - Downloads" />
  </a>
  <br />
</p>

<p align="center">
  <img src="wisent-guard-logo.png" alt="Wisent Guard" width="200">
</p>

A Python package for latent space monitoring and guardrails. Delivered to you by the [Wisent](https://wisent.ai) team led by [Lukasz Bartoszcze](https://lukaszbartoszcze.com).

## Overview

Wisent-Guard allows you to control your AI by identifying brain patterns corresponding to responses you don't like, like hallucinations or harmful outputs. We use contrastive pairs of representations to detect when a model might be generating harmful content or hallucinating. Learn more at https://www.wisent.ai/wisent-guard.  


## License

This project is licensed under the MIT License - see the LICENSE file for details. 

            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/yourusername/wisent-activation-guardrails",
    "name": "wisent-guard",
    "maintainer": null,
    "docs_url": null,
    "requires_python": ">=3.8",
    "maintainer_email": null,
    "keywords": "nlp, machine learning, language models, safety, guardrails, lm-evaluation-harness",
    "author": "Wisent Team",
    "author_email": "your.email@example.com",
    "download_url": "https://files.pythonhosted.org/packages/92/d8/a35f263107ae9a5073062ae6a9136e897d632cb9aaade119f89ad0e726c8/wisent_guard-0.4.3.tar.gz",
    "platform": null,
    "description": "# Wisent-Guard\n\n<p align=\"center\">\n  <a href=\"https://github.com/wisent-ai/wisent-guard/stargazers\">\n    <img src=\"https://img.shields.io/github/stars/wisent-ai/wisent-guard\" alt=\"stars\" />\n  </a>\n  <a href=\"https://pypi.org/project/wisent-guard\">\n    <img src=\"https://static.pepy.tech/badge/wisent-guard\" alt=\"PyPI - Downloads\" />\n  </a>\n  <br />\n</p>\n\n<p align=\"center\">\n  <img src=\"wisent-guard-logo.png\" alt=\"Wisent Guard\" width=\"200\">\n</p>\n\nA Python package for latent space monitoring and guardrails. Delivered to you by the [Wisent](https://wisent.ai) team led by [Lukasz Bartoszcze](https://lukaszbartoszcze.com).\n\n## Overview\n\nWisent-Guard allows you to control your AI by identifying brain patterns corresponding to responses you don't like, like hallucinations or harmful outputs. We use contrastive pairs of representations to detect when a model might be generating harmful content or hallucinating. Learn more at https://www.wisent.ai/wisent-guard.  \n\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details. \n",
    "bugtrack_url": null,
    "license": null,
    "summary": "Monitor and guard against harmful content in language models",
    "version": "0.4.3",
    "project_urls": {
        "Homepage": "https://github.com/yourusername/wisent-activation-guardrails"
    },
    "split_keywords": [
        "nlp",
        " machine learning",
        " language models",
        " safety",
        " guardrails",
        " lm-evaluation-harness"
    ],
    "urls": [
        {
            "comment_text": null,
            "digests": {
                "blake2b_256": "ec618320fa41a3eff6f29f4fb6e86b4213b4511dfcefc0de56f2062d9dd93262",
                "md5": "068018289eed175ed172b48a012684cf",
                "sha256": "5ed4d51043f50be0847063bfda198a26161ae3750fe5894a489af8762fb4d935"
            },
            "downloads": -1,
            "filename": "wisent_guard-0.4.3-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "068018289eed175ed172b48a012684cf",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.8",
            "size": 531865,
            "upload_time": "2025-07-21T23:03:57",
            "upload_time_iso_8601": "2025-07-21T23:03:57.974310Z",
            "url": "https://files.pythonhosted.org/packages/ec/61/8320fa41a3eff6f29f4fb6e86b4213b4511dfcefc0de56f2062d9dd93262/wisent_guard-0.4.3-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": null,
            "digests": {
                "blake2b_256": "92d8a35f263107ae9a5073062ae6a9136e897d632cb9aaade119f89ad0e726c8",
                "md5": "815e87d3107bb1b30ad560f431b5278c",
                "sha256": "78d94222bd4c0c9468fa99112637c53f819fbc78db2e48abc81b5d4959cab410"
            },
            "downloads": -1,
            "filename": "wisent_guard-0.4.3.tar.gz",
            "has_sig": false,
            "md5_digest": "815e87d3107bb1b30ad560f431b5278c",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.8",
            "size": 456132,
            "upload_time": "2025-07-21T23:03:59",
            "upload_time_iso_8601": "2025-07-21T23:03:59.494239Z",
            "url": "https://files.pythonhosted.org/packages/92/d8/a35f263107ae9a5073062ae6a9136e897d632cb9aaade119f89ad0e726c8/wisent_guard-0.4.3.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2025-07-21 23:03:59",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "yourusername",
    "github_project": "wisent-activation-guardrails",
    "github_not_found": true,
    "lcname": "wisent-guard"
}
        
Elapsed time: 0.89485s