Hyper-Extract

Transform documents into structured knowledge with one command.

PlayableOpen source

Description

Hyper-Extract is an LLM-powered knowledge extraction framework that transforms unstructured text into strongly-typed knowledge structures. It supports various output formats including knowledge graphs, hypergraphs, and spatio-temporal graphs, with built-in support for 11+ extraction engines and 80+ domain templates.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: A highly ambitious extraction framework that automates complex graph-based RAG structures across multiple LLM backends.
Attributed to: @yifanfeng97
Built with: GPT-5 Opus 4.8 Sonnet 4.6 Haiku 4.5 3.8 Flash V4-Pro DeepSeek-R1 Qwen3.5 9B
Links: yifanfeng97.github.io
View tweet
View GitHub repo
Tags: #knowledge-extraction #rag #knowledge-graph #python-sdk

Discovered: X
First posted: X · Oct 10, 2026
Listed: Added just now
Build: Strong
Models: Strong

Hyper-Extract

Description

How it grew

Hyper-Extract

Description

How it grew