An intelligent, LLM-powered knowledge extraction and evolution framework with semantic search capabilities
How to install hyper-extract?
yifanfeng97/hyper-extract
$git clone https://github.com/yifanfeng97/hyper-extractInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install hyper-extract by running `git clone https://github.com/yifanfeng97/hyper-extract`, then use it for the current task and follow its documentation at https://github.com/yifanfeng97/hyper-extract.
README.md
| 1 | <div align="center"> |
| 2 | |
| 3 | <a href="https://yifanfeng97.github.io/Hyper-Extract/latest/"> |
| 4 | <picture> |
| 5 | <source media="(prefers-color-scheme: dark)" srcset="docs/assets/logo/logo-horizontal-dark.svg"> |
| 6 | <source media="(prefers-color-scheme: light)" srcset="docs/assets/logo/logo-horizontal.svg"> |
| 7 | <img alt="Hyper-Extract Logo" src="docs/assets/logo/logo-horizontal.svg" width="600"> |
| 8 | </picture> |
| 9 | </a> |
| 10 | |
| 11 | <br/> |
| 12 | <br/> |
| 13 | |
| 14 | **Smart Knowledge Extraction CLI** |
| 15 | |
| 16 | **Transform documents into structured knowledge with one command.** |
| 17 | |
| 18 | [📖 English Version](./README.md) · [中文版](./README_ZH.md) |
| 19 | |
| 20 | <!-- Status ribbon --> |
| 21 | <p align="center"> |
| 22 | <a href="https://trendshift.io/repositories/25420" target="_blank"> |
| 23 | <img src="https://trendshift.io/api/badge/repositories/25420" alt="Trendshift" width="250" height="55"> |
| 24 | </a> |
| 25 | </p> |
| 26 | |
| 27 | <p align="center"> |
| 28 | <a href="https://pypi.org/project/hyperextract/"> |
| 29 | <img src="https://img.shields.io/pypi/v/hyperextract?style=for-the-badge&logo=pypi&logoColor=white&labelColor=1a1a2e&color=3776ab" alt="PyPI Version"> |
| 30 | </a> |
| 31 | <a href="https://python.org"> |
| 32 | <img src="https://img.shields.io/badge/python-3.11%2B-3776ab?style=for-the-badge&logo=python&logoColor=white&labelColor=1a1a2e" alt="Python Version"> |
| 33 | </a> |
| 34 | <a href="LICENSE"> |
| 35 | <img src="https://img.shields.io/badge/license-Apache%202.0-06b6d4?style=for-the-badge&labelColor=1a1a2e" alt="License"> |
| 36 | </a> |
| 37 | <a href="https://yifanfeng97.github.io/Hyper-Extract/latest/"> |
| 38 | <img src="https://img.shields.io/badge/docs-online-3b82f6?style=for-the-badge&logo=readthedocs&logoColor=white&labelColor=1a1a2e" alt="Docs"> |
| 39 | </a> |
| 40 | <a href="https://github.com/yifanfeng97/hyper-extract/stargazers"> |
| 41 | <img src="https://img.shields.io/github/stars/yifanfeng97/hyper-extract?style=for-the-badge&logo=github&labelColor=1a1a2e&color=facc15" alt="GitHub Stars"> |
| 42 | </a> |
| 43 | </p> |
| 44 | |
| 45 | <br/> |
| 46 | |
| 47 | > **"Stop reading. Start understanding."** |
| 48 | > *"告别文档焦虑，让信息一目了然"* |
| 49 | |
| 50 | <br/> |
| 51 | |
| 52 | <img src="docs/assets/hero.jpg" alt="Hero & Workflow" width="800" style="max-width: 100%;"> |
| 53 | |
| 54 | <br/> |
| 55 | </div> |
| 56 | |
| 57 | ## 📰 What's New |
| 58 | |
| 59 | <!-- News snippets are derived from the latest merged PRs. Update as new releases land. --> |
| 60 | |
| 61 | - **🔌 MCP Server** — Query your knowledge abstracts from Claude Desktop and IDE agents with `he-mcp`. *(PR #40)* |
| 62 | - **🧠 Anthropic Claude Support** — Use `claude-opus-4-8`, `claude-sonnet-4-6`, and `claude-haiku-4-5` directly as your LLM provider. *(PR #38)* |
| 63 | - **📝 Obsidian Export** — Turn any graph into an Obsidian vault with Markdown notes linked by `[[wikilinks]]`. *(PR #37)* |
| 64 | - **🧹 `he clean`** — Remove a KA's index or the whole knowledge abstract in one command. *(PR #39)* |
| 65 | - **🔧 Reliability Fixes** — True mean for multi-chunk embeddings, capped OpenAI-compatible batch sizes, and resolved multi-word `llm_*` merge strategies. *(PRs #35, #36, #41)* |
| 66 | |
| 67 | See the full changelog in the [GitHub releases](https://github.com/yifanfeng97/hyper-extract/releases). |
| 68 | |
| 69 | Hyper-Extract is an intelligent, LLM-powered knowledge extraction and evolution framework. It radically simplifies transforming highly unstructured texts into persistent, predictable, and strongly-typed **Knowledge Abstracts**. It effortlessly extracts information into a wide spectrum of formats—ranging from simple **Collections** (Lists/Sets) and **Pydantic Models**, to complex **Knowledge Graphs**, **Hypergraphs**, and even **Spatio-Temporal Graphs**. |
| 70 | |
| 71 | ## ✨ Core Features |
| 72 | |
| 73 | | | | |
| 74 | |:---|:---| |
| 75 | | 🔷 **8 Knowledge Structures** | From simple Lists to advanced Graphs, Hypergraphs, and Spatio-Temporal Graphs | |
| 76 | | 🧠 **10+ Extraction Engines** | GraphRAG, LightRAG, Hyper-RAG, KG-Gen, and more — ready to use | |
| 77 | | 📝 **80+ YAML Templates** | Zero-code extraction across Finance, Legal, Medical, TCM, Industry, and General domains | |
| 78 | | 🔄 **Incremental Evolution** | Feed new documents anytime to expand and refine your knowledge base | |
| 79 | | 📤 **Obsidian Export** | Turn any extracted graph into an Obsidian vault — Markdown notes linked by `[[wikilinks]]` | |
| 80 | |
| 81 | ## 🎯 What Can You Do With It? |
| 82 | |
| 83 | <detai |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
