patents

PatZilla is a modular patent information research platform and data integration toolkit with a modern user interface and access to multiple data sources.

开源中医大模型、数据、新闻、专利合集 (Open-source Traditional Chinese Medical Large Language Models, Datasets, News and Patents hub.)

Automatically download all PDF files of searching results & their patent families found on Google Patents.

专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（dsh, codex, claudecode 等） 调用。

A python tool for reading, parsing and finding patent using the United States Patent and Trademark (USPTO) Bulk Data Storage System.

RAG app for patent similarity search with chatgpt llm over google patents

Unified search, crawling, and archiving toolbox for AI agents and automation scripts.

Official Implementation of PatentLMM (our AAAI 2025 Paper)

The 2024 Google Content Warehouse API leak cross-referenced against 5,456 Google search patents. 848 classified ranking signals, 77,663 extracted patent claims, a 12-stage pipeline, and 26 decision playbooks. Installable as a Claude skill.

Python package to access USPTO bulk data in rectangular format

Graph that downloads patent citation data from USPTO's PatentsView API on-demand and stores it locally in an SQL database (and in memory) for fast access later.

Patent Crawler is a python program to crawl patent information from Google Patent with given keywords.

Scrapes documents from Google patents

Machine Library by Space Frontiers: citable research retrieval for AI agents across papers, books, patents, Wikipedia, and public discussions.

Pitch Track Hack - Pythonic Implementation of the Pitch track used in autotune patent

A Python 3 wrapper for the Patentsview.org API. This script will retrieve the patents for the companies specified (in the form on an excel spreadsheet).

patent claim proofreader and analyzer for 112(b) issues, restrictions, and other issues

Agentic RAG demo for public patent text (Streamlit + hybrid retrieval + verification)

Contains work done on the fintech patents classification project. The goal of this project is to build a model that can detect if a patent is fintech or not based on it's text content. If a patent is fintech then we want to know which kind of fintech patent it is form our defined fintech categories.

AI-assisted pipeline for structured patent claim-to-description correspondence analysis and claim chart prototyping.