Knowledge graphs
669 agents · most starred first
Knowledge graphs, page 7 of 7
PostgreSQL-native GraphRAG: vector search, BM25, and knowledge-graph traversal in a single Postgres database.
A lean GraphRAG library using Postgres/pgvector as the sole database
Hybrid-reasoning knowledge engine: atomic-fact extraction with semantic nuance, ontology normalization, and agentic multi-hop synthesis. No vector database required.
Epistemic Graph RAG with Spreading Activation — retrieval that understands how knowledge relates, not just what it says
A comprehensive system for managing ontologies with multi-tenant support, RESTful API, FastMCP integration, and intelligent navigation capabilities
A knowledge graph management system.
Ratio graph handling in Python.
DataStax RAGStack Knowledge Graph
DataStax RAGStack Graph Store
Python library for RDF Schemas generation from prompts using GPT-3 magic 🪄🪄🪄
Implementation of Haystack Project Specification
Create a Python package.
HelixRAG: Retrieval-Augmented Generation with Graphiti-powered Knowledge Graphs
A package for keyword and ontology comparison.
This package contains tools to work with Tilores entity resolution database within Langchain.
Mapping trait to ontology using GPT.
TrustGraph provides a means to run a pipeline of flexible AI processing components in a flexible means to achieve a processing pipeline.
The ultimate graph library.
A Graph RAG implementation using pure vector search with Milvus
Vital Agent KG Utils
Author and Affiliation retrieval for Whyis
Local-first knowledge base built by an agent over a chosen directory.
DeepAgent Agentic SDK for Wikidata.
File-centric multi-graph manager
America's Law Graph lets you search through every US law from all 50 states and Washington D.C. It combines over half a million statute sections into one easy-t
LangChain-based read-only query layer for LightRAG knowledge graph
LangChain integration for the Diffbot Knowledge Graph and Extract APIs
Local-first AI workspace for knowledge graphs, AI pipelines, and multi-agent coding workflows.
Neo4j graph-store backend plugin for the Orchid AI framework
A knowledge compiler CLI — raw sources in, interlinked wiki out
Knowledge-graph-powered RAG sidecar for infrastructure querying
Typed graph-storage task adapter interface: the repository-style contract (CRUD, typed query execution, introspection) between graph-storage tool capabilities and the substrate.
CLI indexer — uses an LLM agent to read repos/logs/artifacts and populate the coffeectx knowledge graph
Knowledge graph subsystem for Grackle (Neo4j + vector search)
Ontology-guided knowledge graphs and graph-grounded RAG for document intelligence
Neo4j integrations for LangChain.js
LlamaIndex property graph store integration for SynapCores — for GraphRAG.
SemantixRAG v2.0 — AI-Native Data Platform with GraphRAG, Compliance, and Observability
FalkorDB integration for LangChain.js - A blazing fast graph database for AI applications
Reference agent that consumes the Knowledge Context Protocol end-to-end — a deterministic, fail-closed navigation planner plus optional LLM synthesis.
LangChain deepagents that maintain and consult a wiki knowledge base in Open Knowledge Format (OKF).
Global coherence dynamics on networks — Python client for the GraphCoherence API
Document knowledge graphs — extract structured data from documents (Confluence, PDFs, CSV, JSON, Excel) into Neptune
Ontology-driven knowledge-extraction pipeline: paragraphs to a typed, provenance-anchored Knowledge Artifact Graph.
LangChain retriever backed by Compact Knowledge Graphs (CKG) — deterministic, SHA-256 anchored, MCP-native
Paquete que permite trabajar con los Grandes Modelos de Lenguaje (LLM, por sus siglas en inglés) y los Grafos de Conocimiento (KG, por sus siglas en inglés)
PeerPedia Storage GitDB — git + SQLite implementation of ArticleStorage
Graph RAG library leveraging post-graph space sub-grouping and pgvector on PostgreSQL with OpenAI-compatible LLMs.
A local-first, editable knowledge graph for humans and LLMs: npx yamlover <root> serves a browser UI over a plain-text directory, with an editor, live queries, pointers, and an LLM-agent API.
AI-assisted pipeline that converts RDF Turtle (.ttl) knowledge graphs into a ChromaDB vector database
Knowledge-graph-augmented retrieval for RAG systems: Neo4j-backed entity extraction (regex or LLM-based), co-occurrence graphs, entity deduplication, and GraphRetriever for hybrid vector+graph retrieval via the optional ragleap-rag integration. Framework-agnostic, optional multi-tenant namespacing, no hardcoded models or vocabulary.
Curated schema.org warm-agent ontology manifest for Core LLM Wiki: 9 node types, 28 edges, fully schema.org-standard. Data-only.
SDK and CLI for iLiveMyLife Knowledge Graph
A knowledge engine for AI agents: your documents become a git-versioned markdown knowledge graph an agent navigates over MCP, instead of flat vector search.
Ontology-first RAG: extract a governed knowledge graph from documents and serve it over SPARQL and MCP.
Pointer to the pypi package `agentic-graphrag`
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, and resume work across sessions.
Official Python bindings for Graphite: embedded GraphRAG and knowledge graph engine
Graph RAG knowledge base for coding agents, backed by Neo4j and exposed over MCP
The reference engine and command line of AgenticSystemCore: publish a Markdown knowledge Bundle as a static node of the Agentic Knowledge Web — a wiki, an RDF graph, agent memory, skills, MCP and WebMCP tools and a discovery document. Ships the specificat
Custom minimal ontology manifest for an executive agent operating on behalf of a software organization: 21 node types, 42 edges, warm-agent superset. Data-only.
A graph-first LangChain integration for GestaltDB
MeshRAG: Multi-Knowledge-Base Graph RAG, based on LightRAG
Turn a folder of files into a conformant OKF v0.2 knowledge bundle
Placeholder that reserves the name for TenetRAG, a Python SDK for GraphRAG. Not usable yet.
Vinc for Microsoft Agent Framework: bring decisions and records from your knowledge graph into each agent run, without writing anything on its own.
Vinc for LangGraph and LangChain agents: bring decisions and records from your knowledge graph into graph nodes and model calls, and record an episode only when you choose to.
LangChain GraphStore backed by the mushroomdb embedded graph database
LlamaIndex PropertyGraphStore backed by the mushroomdb embedded graph database