Data, search & knowledge

Knowledge graphs

Knowledge graphs build and query knowledge graphs: they extract entities and relationships from unstructured text or code, store them in graph databases, and retrieve connected facts to ground answers. Projects like llm-graph-builder turn raw documents into Neo4j graphs, while graphrag shows how retrieval can follow graph structure instead of flat chunks.

669 agents · most starred first

Top 100 of 669

graphify★ 54,492

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.

graphrag★ 36,699

A modular graph-based Retrieval-Augmented Generation (RAG) system

auto-ontology★ 14,017

Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for LLM and agent workflows.

utopia★ 8,738

World's first open-source enterprise world model.

llm-graph-builder★ 5,318

Neo4j graph construction from unstructured data using LLMs

memgraph★ 4,664

High-performance open-source in-memory graph database for GraphRAG, AI memory, agentic AI, and real-time graph analytics. Cypher-compatible, built in C++.

m_flow★ 4,508

A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

m_flow★ 4,251

A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

Hyper-Extract★ 4,247

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

nano-graphrag★ 4,010

A simple, easy-to-hack GraphRAG implementation

llm-wiki-agent★ 3,718

A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.

Awesome-GraphRAG★ 2,686

Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.

graph-rag-agent★ 2,362

拼好RAG:手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索;整合DeepSearch技术实现私域RAG的推理;自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construction and search. Combine DeepSearch for private RAG reasoning. Create a custom evaluation framework for GraphRAG.

edgequake★ 2,327

EdegQuake 🌋 High-performance GraphRAG inspired from LightRag written in Rust; Transform documents into intelligent knowledge graphs for superior retrieval and generation

llm-wiki-compiler★ 2,275

The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.

helix-foundry★ 2,173

Connect your company's data, let an agent draft an ontology over it, and load it into HelixDB as one graph you can explore and ask questions of. Hosted at foundry.helix-db.com, or run it on your own machine.

Neurite★ 2,169

Fractal Graph-of-Thought. Rhizomatic Mind-Mapping for Ai-Agents, Web-Links, Notes, and Code.

atlas★ 2,163

Apache Atlas - Open Metadata Management and Governance capabilities across the Hadoop platform and beyond

synthadoc★ 1,999

Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.

NLP-Knowledge-Graph★ 1,778

自然语言处理、知识图谱、大语言模型,Agent等技术的前沿追踪、研究与应用。

llm-wiki★ 1,555

LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, querying, and artifact generation.

cite★ 1,338

Ground truth layer for humans and AI agents working together. Version control for knowledge.

neo4j-graphrag-python★ 1,335

Neo4j GraphRAG for Python

youtu-graphrag★ 1,278

[ICLR 2026] Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning

YiGraph★ 1,193

YiGraph is an LLM-driven agent for autonomous Graph Data Analytics based on Analytics-Augmented Generation. 易图(YiGraph)是一套基于 AAG(分析增强生成)框架构建的图分析智能体系统,致力于挖掘数据之间的关联关系,释放数据价值。

semantica★ 1,173

Semantica 🧠 — AI-native knowledge graph intelligence framework for semantic retrieval, ontology reasoning, context graphs, and explainable AI systems.

pgGraph★ 1,090

Open-source graph database superpowers for your existing Postgres data.

GraphRAG-SDK★ 1,036

Build fast and accurate GenAI apps with GraphRAG SDK at scale 🌟

KG_RAG★ 950

Empower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks

ChatIE★ 935

The online version is temporarily unavailable because we cannot afford the key. You can clone and run it locally. Note: we set defaul openai key. If keys exceed plan and are invalid, please tell us. The response speed depends on openai. ( sometimes, the official is too crowded and slow)

AutoSchemaKG★ 849

This repository contains the implementation of AutoSchemaKG, a novel framework for automatic knowledge graph construction that combines schema generation via conceptualization.

robot★ 820

知识图谱问答机器人,聊天机器人,基于知识图谱、语义理解等的对话机器人。

sift-kg★ 809

Turn any collection of documents into a knowledge graph. Extract entities and relationships via LLM, deduplicate with your approval. Map domains, find hidden connections, spot patterns across documents — knowledge that persists and compounds, for you and your AI agents. All from the CLI.

carrel★ 808

Ontology-Augmented Generation for AI agents.

Nucleoid★ 762

Logic Language for LLMs 🌱🐋🌍 Build Neuro-Symbolic AI for Learning and Reasoning

knowledge-graph-from-GPT★ 688

Using GPT to organize and access information, and generate questions. Long term goal is to make an agent-like research assistant.

sage-wiki★ 658

sage-wiki is a graph memory and knowledge base that AI agents and humans build and query together. Drop in documents; an LLM compiler turns them into an interlinked wiki with a knowledge graph. One Go binary scales it from a personal vault to a team hub to a company knowledge graph.

Kwipu★ 614

Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.

Graph-R1★ 600

[ICML 2026] Official resources of "Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning".

neo4j-python-pandas-py2neo-v3★ 580

Excel-to-Neo4j knowledge graph examples: legacy py2neo v3 plus modern Neo4j GraphRAG/vector search.

graph-engineering★ 576

Graph engineering for AI agents: the 9-stage knowledge-graph pipeline (translated from SEU's graduate course) + task-graph orchestration patterns, as a Claude skill with teaching mode and paste-ready workflows

LinearRAG★ 572

[ICLR 2026] LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora

HiRAG★ 552

[EMNLP'25 findings] An easy-to-use Graph RAG system using hierarchical knowledge.

context-ontology-accelerator★ 481

An open-source, ontology-based semantic context accelerator that enables AI agents to make more accurate, consistent, and explainable decisions.

ontobricks★ 479

Transforms Unity Catalog tables into a dynamic, understandable knowledge graph, with ontology design and reasoning exposed to AI agents as MCP tools

Large-Language-Models★ 476

xLLM 1.0, smart crawling, knowledge graph discovery.

graphrag-toolkit★ 467

Python toolkit for building graph-enhanced GenAI applications

UnifiedModel★ 466

The semantic layer that makes enterprise data understandable to AI agents — model entities and relations once, query through SPL/MCP/REST, and connect telemetry, services, and business objects in one object graph.

SmartKG★ 440

This project accepts excel files as input which contains the description of a Knowledge Graph (Vertexes and Edges) and convert it into an in-memory Graph Store. This project implements APIs to search/filter/get nodes and relations from the in-memory Knowledge Graph. This project also provides a dialog management framework and enable a chatbot based on its knowledge graph.

chat2graph★ 430

Chat2Graph: Graph Native Agentic System.

graphrag-visualizer★ 430

A web-based tool for visualizing and exploring artifacts from Microsoft's GraphRAG.

wiki-graph★ 427

distill any book down to its spine

rushdb★ 376

The database for AI: graph, vector and analytics on the same records, with a live schema of labels, fields and values that agents read before they query. One Rust binary, Apache-2.0.

GraphAgent★ 373

[EMNLP2025] "GraphAgent: Agentic Graph Language Assistant"

vector-graph-rag★ 332

Graph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.

Hyper-RAG★ 331

"Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation" by Yifan Feng, Hao Hu, Shihui Ying, Xingliang Hou, Shiquan Liu, Mingyuan Yang, Junchang Li, Shaoyi Du, Nanning Zheng, Han Hu, and Yue Gao.

VeritasGraph★ 326

VeritasGraph — open-source Knowledge Graph & GraphRAG framework on GitHub. Build multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over your own data. Nodes, edges, RDF, linked-data — runs locally or in the cloud.

gfm-rag★ 314

[NeurIPS'25, ICLR'26] Graph Foundation Model for Retrieval Augmented Generation

Graph-CoT★ 311

Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs (ACL 2024)

KG-Pipeline★ 306

Converting Unstructured Data to a Knowledge Graph: An End-to-End Pipeline

qKnow★ 300

qKnow is an open-source agent platform for enterprise knowledge intelligence and industry AI. It provides knowledge graphs, RAG, and bot building, encapsulating industry AI into standardized modules for rapid deployment. Supporting unified integration of documents and data, it helps enterprises quickly build knowledge hubs and AI solutions.

openDomain★ 297

Git-native, evidence-backed domain semantic layer for AI agents and human maintainers.

ontocast★ 261

Agentic Ontology Assisted Framework for Semantic Triple Extraction

llm-movieagent★ 246

Semantic layer on top of a graph database to provide an LLM with a set of robust tools to interact with the database

What-to-eat-today★ 241

🍽️基于图RAG技术的AI美食推荐助手 - Datawhale all-in-rag教程实战案例,集成Neo4j图数据库、Milvus向量检索与智能对话系统

ksor★ 235

KSoR (Knowledge System of Record) is an open-source SDK for building governed, authoritative knowledge systems for humans and AI agents. It is a foundation of an AI-native knowledge platform.

MemGraphRAG★ 234

[KDD 2026] MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation

knowledge-graph-of-thoughts★ 232

Official Implementation of "Affordable AI Assistants with Knowledge Graph of Thoughts"

GraphRag.Net★ 230

参考GraphRag使用 Semantic Kernel 来实现的dotnet版本,可以使用NuGet开箱即用集成到项目中

operational-ontology★ 215

A minimal, readable reference implementation of the Operational Ontology pattern. Palantir Foundry is one implementation; this is the concept, minimized.

flexible-graphrag★ 203

GraphRAG, RAG, LlamaIndex, LangChain, 15 Prop Graph, 4 RDF, 10 Vector, 3 Search DBs. 14 data srcs, auto sync, Alfresco, Nuxeo, SharePoint, Box, CMIS, S3,GCS,Azure, web. KG auto-bld, Ontologies, 13 LLM providers, Docling, LlamaParse, LiteParse, Hybrid Search, AI Chat. TypeScript React, Vue, Angular, Python, REST, MCP, OpenArch, Langflow, CocoIndex.

Personal_External_Brain★ 200

Not another ChatGPT wrapper. This is a local-first tool that turns your notes, web pages, PDFs and audio/video into a personal knowledge graph — running entirely on your own machine.

diffbot-kg-chatbot★ 199

Knowledge graph construction and RAG demo using Diffbot and Neo4j

OneKE★ 199

[WWW 2025] A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System.

kg-rag★ 199

Supporting repository for the Essential GraphRAG book published by Manning

NeoGPT-Explorer★ 189

Knowledge-graph based chatbot using GPT3 and Neo4j

graphrag-practice-chinese★ 188

GraphRAG的应用实例,项目特点在于提供了替换OpenAI模型的方法,并通过修改原有提示和切分文档的方法,提高了GraphRAG处理中文内容的能力。

SubgraphRAG★ 187

[ICLR 2025] Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

ontopoc★ 182

Ontology tool for MCP / Claude: draft, check, and confirm ontologies from business data. Schema work ahead of a knowledge graph or semantic layer.

openhikmah-web★ 181

An AI-powered Quran knowledge graph — place verses on a canvas and discover thematic, linguistic, and theological connections.

Cairn★ 181

Open-source GraphRAG domain knowledge layer: LLMs continuously distill scattered skill docs into a queryable, evolvable, human-editable two-layer knowledge graph — versioned, hot-swapped and rolled back via a GitOps pipeline like software releases, and served to AI agents over MCP. RAG, but with relational structure.

GraphRAG-Breakdown★ 180

A breakdown of knowledge graph RAG with diagrams and examples

llm-wiki-newsroom★ 176

Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls published pages back in before they go stale — writer ≠ reviewer, local-first, a structured alternative to RAG.

engraph★ 175

Local knowledge graph for AI agents. Hybrid search + MCP server for Obsidian vaults.

langchain-graphrag★ 174

GraphRAG / From Local to Global: A Graph RAG Approach to Query-Focused Summarization

LLM-KG4QA★ 167

[EMNLP2025] LLM-KG4QA: Large Language Models and Knowledge Graphs for Question Answering

NeoGPT-Recommender★ 155

Context-aware knowledge-graph based chatbot using GPT4 and Neo4j

RAGU★ 147

[EMNLP 2026] Modular GraphRAG framework

instagraph-nextjs-fastapi★ 143

Generate knowledge graphs. Inspired by @yoheinakajima instagraph.ai

SimGRAG★ 142

Official code of the ACL 2025 paper "SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation"

KARMA★ 139

Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment

graphrag-legalcases-postgres★ 128

Legal Research Copilot Example Solution built with Generative AI capabilities of PostgreSQL on Azure

ai-toolkit★ 119

Open-source tools for AI on Memgraph: persistent agent memory, knowledge graphs, GraphRAG, and integrations for LangChain, LightRAG, and MCP.

braindb★ 117

An "LLM wiki" upgraded to a real database — typed entities, graph relations, HTTP API, and a built-in natural-language agent.

lic2019-competition★ 114

2019语言与智能技术竞赛-基于知识图谱的主动聊天

graphrag-api★ 113

GraphRAG Server

biomedical-graphrag★ 107

A comprehensive GraphRAG (Graph Retrieval-Augmented Generation) system designed for biomedical research

gibram★ 107

GibRAM is an in-memory knowledge graph server designed for retrieval augmented generation (RAG / GraphRAG) workflows.

GraphSearch★ 100

GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation

ontology★ 100

开源的企业级可运行本体平台:统一建模业务语义,接地企业真实数据,并通过 MCP、SDK 向 AI Agent 提供可治理的逻辑与行动能力。

More in Data, search & knowledge