Data, search & knowledge

Knowledge graphs

669 agents · most starred first

Knowledge graphs, page 2 of 7

open-graph-memory★ 97

OpenGraphMemory : Self-hosted knowledge graph extraction, temporal graph storage, and agent memory platform.

agent-knowledge-hub★ 96

企业级多Agent知识管理系统:4个AI Agent协作完成文档解析→知识抽取→智能问答→增量更新,Python/Java/Go三语言实现

Alfred★ 95

Alfred: An open-source Data Assistant for domain adoption, powered by agent skills, semantic knowledge graphs and relational data.

ToG-3★ 95

Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval

browsegraph★ 93

In-browser GraphRAG

context-aware-rag★ 93

Context-Aware RAG library for Knowledge Graph ingestion and retrieval functions.

ESEILANE★ 93

High-performance Knowledge Graph engine for AI, LLMs, and GraphRAG — built for the next generation of intelligent applications.

chatbot★ 92

知识图谱 neo4j 答案查找 + 机器学习 分类模型 问题分析 = 电影知识库问答机器人

OntoFlow★ 92

基于时序动态的图计算和图谱数据库引擎AbutionGraph,将实体 - 组件 - 系统与基于流的 AI 编程深度结合,构建可演进的数字孪生与世界模型。构建以本体驱动为核心,串联实时数据、业务逻辑与智能 Agent,实现从数据源探知、知识库、记忆编程、智动化工作流到实时业务推理与行动决策的全链路闭环。

nebula-siwi★ 91

Siwi (/ˈsɪwi/) is a PoC of Dialog System With Graph Database Backed Knowledge Graph.

graph-rag★ 91

Graph traversal for improved RAG

StruInfo★ 91

Self-hosted, traceable document-to-knowledge workspace with deterministic workflows, optional AI, search, RAG, and an editable knowledge graph.

iGraph★ 89

iGraph is a Graph Data Agent for natural-language graph construction, analysis, and learning. Explore built-in experiences for Financial Risk Control, AI for Science, and Relationship Insights, with prepared graphs, example questions, interactive visualization, and evidence-based explanations.

mykg★ 86

MyKG Knowledge Graph Engine: Turn raw files into knowledge graphs with induced ontology

EvoGraph-R1★ 85

This repository contains the code for the paper "EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval"

GraphAugmented-Legal-RAG★ 83

Create a knowledge graph out of unstructed legal text - use said knowledge graph in a graph augmented retrieval augmented generation pipeline

neo4j-ai-experiments★ 81

Examples of my tutorial on how to use Neo4j for empowering AI RAG systems

obsidian-vault-intelligence★ 81

Obsidian vault intelligence

kglite★ 81

Embedded Cypher knowledge graph for Python and Rust. Bundled MCP server, describe() schema, and code-graph parser for LLM agents.

Awesome-Graph-augmented-LLM-Agent★ 79

[IEEE Intelligent Systems] Awesome-Graph-augmented-LLM-Agent (GLA)

atlas-knowledge-base-agent★ 78

The ATLAS Agent helps answer questions about the MITRE ATLAS Framework by leveraging the ATLAS Knowledge Graph.

openmapstack-skills★ 78

AI-agent skill for reproducible, validated GIS analysis — from authoritative data discovery to interactive maps, on an open-first geospatial stack (OSM, Overture, STAC, DuckDB, PostGIS, QGIS, MapLibre).

GoG★ 76

Generate-on-Graph: Treat LLM as both Agent and KG for Incomplete Knowledge Graph Question Answering. EMNLP 2024 Main

LegalGraphRAG★ 74

[ACL'26 Main] Official code for "LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning".

compass★ 73

Compass is a context engine that builds a knowledge graph of your organization's metadata, capturing entities, relationships, and lineage across systems and time, making it discoverable and queryable for both humans and AI agents.

AgentRE★ 69

Repo for for paper "AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction".

agentic-knowledge-graph★ 69

Knowledge-graph RAG built from structured metadata instead of LLM extraction. 929M edges, zero LLM calls, 83.2% on held-out PubMedQA. Case study: the full PubMed 2026 baseline.

MediGraphRAG★ 68

构建一个医疗知识图谱并基于此实现 RAG,并以此实现医学试题的生成

a1facts★ 67

a1facts - the precision layer for AI agents

KGB-RAG★ 65

KGB-RAG是一个基于neo4j图数据库和其他图数据库的知识图谱检索系统,它可以根据用户的自然语句提问,从原数据库获取相关实体信息,并通过知识图谱检索技术以及结合大模型自身能力来增强回答用户的自然语言提问。

llm4ea_official★ 64

[NeurIPS‘24] LLM4EA: Entity Alignment with Noisy Annotations from Large Language Models

zissa-wiki★ 63

Zissa Wiki — an LLM-maintained research knowledge base in plain markdown, maintained by any AI agent (Claude, Codex, Gemini, DeepSeek, Kimi, Grok, Mistral or any chat app). Implements Karpathy's LLM Wiki pattern; checks every quote against its source.

go-light-rag★ 62

A Go library implementation of LightRAG - an advanced Retrieval-Augmented Generation (RAG) system that uniquely combines vector databases with graph database relationships to enhance knowledge retrieval.

agentic-graphrag★ 60

Agentic GraphRAG is an open source framework that builds a graph connecting your enterprise knowledge to the conversations your agents have and the decisions they make. Each decision links back to the passages and task events behind it, so agents can look up earlier decisions with their evidence, resume work across sessions.

seocho★ 59

Ontology-aligned middleware for agentic graph memory. Python SDK, runtime, and reproducible indexing/query experiments.

DyG-RAG★ 58

Code implementation for DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning.

knowledge-graph★ 56

A minimal implementation of GraphRAG, designed to quickly prototype whether you're able to get good sense-making out of a large dataset with creation of a knowledge graph.

ConsciousDB★ 56

A database-agnostic Agentic GraphRAG framework using swappable System One models (local Laya / cloud Jev). A plug-and-play intelligence layer featuring a complete 4-phase pipeline, continuous evaluation and custom A* traversal for any graph database.

kg-rag★ 54

Exploratory implementations of knowledge graph RAG (entity-based, Cypher, GraphRAG) and baselines on SEC 10-Q filings. Companion code to the Vector Institute post 'Enhancing RAG with knowledge graphs'. Archived.

MedicalGraphRAG★ 54

自主实现面向医学知识的GraphRAG应用系统#大模型LLM#RAG#GraphRAG#Agent智能体#知识图谱KG

KGARevion★ 53

KGARevion: AI Agent for Knowledge-Intensive Biomedical QA

laya-jev-GraphRAG★ 53

A database-agnostic Agentic GraphRAG framework using swappable System One models (local Laya / cloud Jev). A plug-and-play intelligence layer featuring a complete 4-phase pipeline, continuous evaluation and custom A* traversal for any graph database.

abap_wiki★ 51

Agent-driven SAP/ABAP knowledge base engine that turns S/4HANA custom objects into citable Markdown/Obsidian context for humans and AI agents.

yfiles-graph-for-create-llama★ 50

An interactive integration of yFiles for HTML with LlamaIndex to visualize the knowledge graph used for query resolution.

agentic-kg★ 50
PixlieAI★ 48

Please check our new project with similar targets: https://github.com/pixlie/Pixlie

langchain-graphrag-baml★ 48

Improving langchain knowledge graphs using baml

GraphTeam★ 47

Official Repository of "GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration".

librarian★ 47

The life-sciences knowledge layer for AI agents

AMG-RAG★ 45

AMG-RAG (Agentic Medical Graph-RAG) is a comprehensive framework that automates the construction and continuous updating of Medical Knowledge Graphs (MKGs), integrates reasoning, and retrieves current external evidence for medical Question Answering (QA).

DKGR★ 44

Learning to Walk with Dual Agents for Knowledge Graph Reasoning (AAAI'22)

garnet-framework★ 44

The Garnet Framework is an open-source framework that enables you to build living digital twins and context-aware solutions through dynamic knowledge graphs.

cdkg-challenge★ 43

Let’s build a curated Knowledge Graph based on the collective wisdom of 260+ experts

ngest★ 42

Python script for ingesting various files into a semantic graph. For text, images, cpp, python, rust, javascript, and PDFs.

graphrag-light★ 42

A GCP native, modular, parallelized Graph RAG implementation.

NodeGraph★ 42

Turn research papers into verifiable knowledge graphs with AI.

schema-miner★ 40

A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models

The-Brain★ 40

A multimodal RAG dashboard and interactive 3D Knowledge Graph. Process documents locally with Ollama or via Cloud APIs, powered by LightRAG, RAG-Anything and Neo4j.

ctxgraph★ 40

privacy-first context graph engine for AI agents and human teams.

ai-xf-format★ 40

AI-XF, the AI eXchange Format. A strict superset of Google's Open Knowledge Format (OKF) v0.2: stable identity, typed relationships, provenance, media identity, federation with evidence. Every AI-XF bundle is a valid OKF bundle.

agentic-graph-rag★ 39

Agentic Graph RAG: Skeleton Indexing + VectorCypher + Agentic Router with Self-Correction

unified-kg-rag-on-aws★ 39

AWS-native knowledge graph RAG framework. Runs GraphRAG, LightRAG, HippoRAG 2 and RAPTOR on one shared index, each selectable at index and query time, with hybrid BM25 + vector + graph retrieval and source provenance. Amazon Bedrock, Neptune and OpenSearch, or fully local. Incremental indexing, multilingual, bring-your-own KG, built-in evaluation.

ontorag★ 37

ontorag cli and core library

LLMKGraph★ 37

Knowledge graph-augmented retrieval for evidence-based AMD information: LLM-built causal KG, Graph-RAG chatbot, LLM comparison (IEEE Access 2025)

ongrid★ 36

ONGRID — Ontology-Native Graph · Retrieval · Inference · Decision. 3D knowledge graph + zero-token ZTC answer verification. by VIDRAFT.

14-rag-failures★ 35

Encountering 14 different Naive RAG fails and using KG to solve it

DepsRAG★ 34

Interactive LLM Chatbot that constructs direct and transitive software dependencies as a knowledge graph and answers user's questions leveraging RAG and critic-agent approach

knowledge-graphs★ 34

Create and interact with Knowledge Graphs using Generative AI

JusChat★ 34

JusChat é um assistente jurídico inteligente baseado em tecnologia GraphRAG (Graph Retrieval Augmented Generation) que utiliza processamento de linguagem natural e grafos de conhecimento para consulta e análise de documentos jurídicos brasileiros.

KnowLion★ 34

基于动态图数据库的动态超图知识检索系统,特性:五重检索内核(Vector语义、BM25关键词、Graph动态推理、上下文关联、实体多跳推理)、全属性实时演化、Agent语义重叠率智能自维护机制、轻量化超图架构。

stable-cypher-instruct-3b★ 34

transformers safetensors gguf stablelm text-generation causal-lm

chatbot★ 33

kbqa task-oriented qa seq2seq ir neo4j jena seq2seq tf chatbot chat

khive★ 33

A knowledge graph your AI agents build, query, and grow. Built for agents that need structure beyond vectors

GraphRAG-Agent★ 33

GraphRAG Agent 是一个面向私有知识库的全栈图谱问答系统。它将文档上传、文本解析、分块、知识图谱抽取、索引任务编排、可视化编辑和问答记录整合在一个受认证保护的工作流中,并为多用户场景提供用户自带 API Key(BYOK)能力。

CausalAgent★ 32

这是一个由LangGraph协议主导的因果分析Muti-Agent,结合MCP,RAG等多种工具进行辅助进行因果分析,提供给用户一份完善的因果分析的分析报告和因果图

graphrag-engineering-pdfs★ 32

Ontology, and Knowledge graph based RAG that uses local LLM.

graqle★ 32

Persistent organisational intelligence for AI agents. Turn codebases, documents, policies and decisions into a knowledge graph — 13 LLM backends, impact analysis, evidence + confidence. Works with Claude Code, Cursor, Copilot.

mind_mapper★ 31

Network Analysis through LLMs for Knowledge Extraction

MAKGED★ 31

MAKGED is the first multi-agent framework for collaborative error detection in knowledge graphs.

nen-db★ 31
Interactive-KBQA★ 31

A KBQA solution framework based on the agent-environment paradigm in the era of LLMs.

kontext-brain-ts★ 31

TypeScript knowledge graph RAG for AI agents: source evidence, hybrid retrieval, MCP integration, and a permission-aware PostgreSQL runtime.

rudradb-opin-examples★ 30

rudradb-opin-examples is for example implementations of the pip install rudradb-opin

graphrag-kyc-agent★ 30

An agent built with OpenAI Agent SDK, Neo4j and Neo4j MCP server

agentic-graph-rag-skills★ 30

Companion repo for Agentic Graph RAG (O'Reilly, Anthony Alcaraz & Sam Julien) — 50 runnable skills + 8 pedagogical notebooks covering all eight chapters, on one moto-mocked AWS DevOps scenario

Common_Chronicle★ 29

Common Chronicle turns messy context into structured, sourced timelines.

brick-llm★ 29

brickllm with langgraph

Chatbot★ 28

基于语义理解、知识图谱的聊天机器人

phenomics-assistant★ 28

LLM retrieval augmented generation agent for the Monarch Knowledge graph.

clinical-agent★ 28

This project is designed for a simple LLM agent with tools on a clinical knowledge graph in Neo4j.

hands-on-lab-neo4j-and-microsoft★ 28

Hands on Lab for Neo4j and Microsoft

ontology-llm★ 28

Agent-OM: Leveraging LLM Agents for Ontology Matching

GenAIMindMapFlowBuilder★ 27

GenAI Mind Map Flow Builder uses LLMs (OpenAI & Google Gemini) to generate intelligent mind maps from diverse sources like PDFs, SQL, CSVs, media, and websites. Built with FastAPI and ReactJS, it visualizes key ideas and relationships for data analysis and knowledge discovery.

Graph-RAG-Engine★ 27

An explainable AI system that combines Graph Intelligence, Vector Search, and Retrieval-Augmented Generation (RAG) to deliver grounded answers and transparent reasoning paths. Includes a FastAPI backend, Streamlit UI, FAISS vector index, and an in-memory knowledge graph for hybrid retrieval and recommendations.

GSearchAI★ 27

Open-source enterprise AI search & Graph RAG platform. Self-hosted alternative to Glean, GoSearch & Guru — Neo4j + pgvector hybrid retrieval, active ontologies, multi-tenant RLS isolation, explainable multi-hop answers. MIT licensed.

gephi-ai★ 27

Extends Gephi with AI capabilities. Includes a Gephi plugin for graph analytics, an MCP server bridging AI assistants and Gephi, an agentic AI plugin with slash commands and workflow skills, and a specialized agent for network analysis research. Built for researchers working across network science and AI.

novel-config-copilot★ 27

网文平台资源配置决策助手:GraphRAG 两阶段检索 + ReAct Agent + 规则引擎兜底,方案合法率 60%→100%

Knowledge-Based-QA-System-with-Python-and-Prolog★ 26

This project is a simple implementation of a knowledge-based system. It is a simple ChatBot. There is a prolog file that defines the knowledge base. The questions are handled with python. The key idea is mapping different questions for the same answer. The simplest way is finding keywords in the question. Using the keywords, a query is performed on the prolog knowledge base. Then the query result is shown with some prefix and suffix as the answer.

KnowledgeGraphQA-Langgraph★ 25

AI-powered system generating knowledge graphs from text and answering questions.

End-to-End-Graphrag-implementation★ 25

End-to-End-Graphrag-implementation

More in Data, search & knowledge