semantic-extraction

Agent-ready CLI for static page inspection, search triage, and browser handoff.

Cite Lens: An AI Tool for Detecting Out-of-Scope and Out-of-Context Citations; Conference paper accepted at TPDL 2025

Semantic Extraction & Data Unification

Agent-readable semantic browser layer for AI agents — token-efficient web understanding, semantic snapshots, persistent sessions, and MCP/CLI/Python APIs.

A new package that enables users to input textual descriptions of visual design, layout, or interface concepts and returns structured representations or annotations derived from the description. It le

This is the code for the basic HPO agent demo demonstrated at HDUG November 2025 as a taster of future agent-based data extraction possibilities which are already well on their way.

Metadata and semantic intelligence layer for MailPlus without duplicating raw mail.

Medical, legal, finance docs, LLM Wiki — semantic skeleton first, before GraphRAG or graphify. 30%+ more nodes & communities.

Text-to-Knowledge-Graph: Extract semantic relationships (SVO triples) from domain-specific text and build knowledge graphs with network analysis metrics.

A repository containing environmental imagery segmentation using several apis.

High-performance Python normalization engine for Agent-Commerce-OS. Handles semantic extraction, HTML parsing, and structured RAG output.

A local-first EPUB study companion that turns book sections into structured, LLM-ready Markdown packets