# yifanfeng97/Hyper-Extract

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

Repository: https://github.com/yifanfeng97/Hyper-Extract
Canonical: https://ross.abutalabs.com/products/hyper-extract
Homepage: https://yifanfeng97.github.io/Hyper-Extract/
Language: Python
License: NOASSERTION
License Family: other
Topics: ai, cli, hypergraph, information-extraction, knowledge, knowledge-graph, llm, python, rag, ai-agents
Last push: 2026-08-12T02:08:38+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 83, longevity 17
- inputs: {"age_days": 238, "days_push": 22, "days_rel": 32, "gap_med": 32, "n_releases_24m": 6}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3376, forks 398 (observed 2026-08-28T04:07:58.523142+00:00)

## What it is
Hyper-Extract is a Python CLI tool that transforms unstructured documents into structured knowledge using LLMs, producing graphs, hypergraphs, and spatio-temporal extractions with a single command. It supports multiple LLM providers (OpenAI, Anthropic, DeepSeek), exports to formats like Obsidian vaults, and includes an MCP server for querying knowledge abstracts from AI agents.

## Use cases
- extract knowledge graphs from unstructured documents
- build a hypergraph from text with an LLM
- convert PDFs and notes into structured knowledge
- query extracted knowledge from Claude Desktop via MCP
- export a knowledge graph to an Obsidian vault
- build RAG-ready knowledge bases from documents

## When to choose
- you want one-command extraction of structured knowledge from messy text
- you need hypergraph or spatio-temporal extraction beyond plain knowledge graphs
- you want LLM-provider flexibility including Claude and DeepSeek
- you want to feed extracted knowledge into AI agents via MCP

## When to avoid
- you need a fully managed GUI-based knowledge graph platform
- you want deterministic extraction without LLM costs or API dependencies
- you need a non-Python or embedded environment

## Facets
- artifact type: cli-tool
- maturity: active
- function: nlp, rag, cli, llm-inference, mcp, search-engine
- domain: large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: knowledge-graph, hypergraph, information-extraction, obsidian-export, unstructured-text, natural-language-processing, knowledge-graphs, retrieval-augmented-generation

## Member repositories
- yifanfeng97/Hyper-Extract (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:58.523142+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:39:43.772374+00:00, confidence not recorded.
  - readme: https://github.com/yifanfeng97/Hyper-Extract (fetched 2026-08-28T04:07:58.523142+00:00, sha a5a900f70861)
  - homepage: https://yifanfeng97.github.io/Hyper-Extract/ (fetched 2026-08-29T09:33:36.732387+00:00, sha 36c6c3c2e4f9)
- Data as of 2026-08-30T08:39:29.467469+00:00.