Fix broken markdown that LLMs generate — tables, lists, headings, emphasis, code fences, quotes. Zero dependencies, one function.
MoverScore: Evaluating text generation with contextualized embeddings and earth mover distance
Production-ready AI agent framework with comprehensive testing, intelligent caching, connection pooling, unified interfaces, 36+ tools, and enterprise-grade security - 30-50% cost savings through smart optimization
261 CLI tools — data analysis, CSV, JSON, sysmon, passwords, batch rename, charts — zero deps, one pip install
Various tools for filesystem, io, processes, other stuff.
The analysis library, engine and command line behind PyAT: TDT fibre photometry, Oxysoft NIRS, Terranova EFNMR and text-field studies, with provenance records (formerly PhysicsLibrary)
A library for augmenting text for natural language processing applications.
A structural approach to signal ML
A library for standardizing terms with spelling variations using a synonym dictionary.
Save clipboard content (text and images) to files with smart format detection
中文情感分析库(Chinese Sentiment))可对文本进行情绪分析、正负情感分析。
Process-Sanskrit is python library for automatic Sanskrit text annotation and inflected dictionary search
Basic tools for working with natural language text data
A package for processing large corpora and detecting passive voice.
A ridiculously simple search engine factory
0x1NLP: Indonesian natural language preprocessing for Python
SnakeEats unified service: single-process single-port WS JSON-RPC (text streams x tool registry)
Voice AI Platform - Local STT/TTS with Chinese Language Support
Scan and process embedded processing instructions in Text documents.
This package offers editor tools helping users write Steam guides and reviews. Support Steam information queries, image editing tools, and BBCode text processing tools.
An autonomous MCP agent that provides token-efficient code analysis, documentation retrieval, and implementation guidance for large library repositories using a dedicated OpenAI-compatible LLM.
Gyokusai: A Web-Scale Text Processing Library
A simple and efficient Python SDK for DeepSeek-OCR API
Quid is a tool for quotation detection in texts and can deal with common properties of quotations, for example, ellipses or inaccurate quotations.
Intelligent Markdown chunking library for RAG systems
Accurately extract complete noun phrases with customisation and strctural output.
Measuring corpus similarity in Python
Enterprise-grade text classification library with 11+ LLM providers, streaming, monitoring, and advanced workflows
high quality multi-lingual speech to text
A library for processing and analyzing scientific documents
Framework for build NLP information extraction systems using regular expressions.
Artificial Intelligence a Modern Approach 4th Ed by Peter Norvig and Stuart Russel
High performance BPE tokenizer written in Rust with Python bindings
NLP utilities and examples for _Natural Language Processing in Action, 2nd Ed_, by Hobson Lane and Maria Dyshel
Python toolkit for AI-assisted applications - an OpenAI-compatible LLM client, text processing, web scraping, and interactive demos
HanDic package for installing via pip.
Local-first vision-language pipeline inspired by VL-JEPA. Compress images, text, conversations, and RAG documents locally via Ollama before sending to any LLM API. Deterministic, fact-preserving token optimizer plus MCP server, FastAPI server and video processing.
Fast PaddleOCR MCP server - Extract text from images using PaddleOCR with optimized performance
LLM integration for twat
High-fidelity context-aware chunking and interactive visualization for RAG. Advanced segmentation for code and documents, because your LLM is only as smart as the fragments you feed it.