🔧 Manage Claude Code, Codex, and Gemini CLI configurations effortlessly with this powerful command-line tool. Simplify your workflow and enhance productivity.

📄 Simplify contract review with SLA-CARA, an AI assistant that classifies clauses, summarizes content, assesses risks, and extracts key insights.

🧠 Extract named entities from text effortlessly with advanced NLP and ML models, providing insights and analytics for diverse documents.

🧠 Enhance your applications with spaCy, a powerful library for advanced Natural Language Processing in Python and Cython, supporting 70+ languages.

🔍 Analyze PDF files effectively with this Python tool, testing compatibility across libraries to guide optimal PDF processing solutions.

🔄 Switch and manage Claude Code configurations easily with CC CLI, featuring multi-site support, smart merging, and cloud backups.

🚀 Prototype and deploy generative AI applications with ease using Python, Gradio, and Transformers for text, image, and speech tasks.

A self‑hosted search engine for documents

AI pipelines for Omeka S digital collections - OCR correction, entity extraction, and text analysis

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

A Python library to use pre-trained, small task-specific LLMs and fine-tune them without training data 🤖🚀

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

Simplifying Persian NLP for Modern Applications

Python AI, ML, DL and NLP exploration playground.

Anonymises data inside text files and in sheet files. It recognises and removes various sorts of personally identifiable information (PII). Each removed part is replaced with suitable pseudonyms, depending on the type of removed data. Currently English and Russian languages are supported. Russian works both with Cyrillic and Latin characters.

This package features data-science related tasks for developing new recognizers for Presidio. It is used for the evaluation of the entire system, as well as for evaluating specific PII recognizers or PII detection models.

DE-NERmed: An OpenNLP named entity recognition tool and model files trained for medical NLP use cases

This project involves using Natural Language Processing to attempt to quantify character relationships in the story Worm. It contains the code files for generating the results, and the static files for the github pages website.

A fast CPU-based API for Qwen 2.5 using CTranslate2, hosted on Hugging Face Spaces.