Skills
.Work. You
Rest

graphmemory

Community

Embed and query GraphRAG knowledge graphs

Software Engineering#deduplication#knowledge-graph#graph-database#vector-search#dspy#graphrag#graphmemory
AuthorbradAGI
Version1.0.0
Installs0

System Documentation

What problem does it solve?

GraphMemory provides an embedded GraphRAG knowledge graph platform built on DuckDB that combines vector, full-text, and hybrid search to store, retrieve, and reason over entities and relationships.

Core Features & Use Cases

  • Vector search across node vectors using HNSW with cosine, L2, or inner product metrics.
  • Full-text search across node properties with BM25.
  • Hybrid search that blends text and vector similarity for more relevant results.
  • GraphRAG retrieval pipeline: hybrid search, graph expansion, context assembly, and LLM Q&A.
  • DSPy-based extraction to populate graphs from unstructured text.
  • Graph algorithms (PageRank, centrality, components) via NetworkX (optional).
  • Merge/upsert of nodes and edges with fuzzy deduplication and upsert semantics.
  • Import/export formats (JSON, CSV, GraphML) and a browser-based visualizer.
  • Transactional safety with retry for transient errors.

Quick Start

Install graphmemory and create a GraphMemory instance, add a few Node/Edge objects, and run a simple retrieve or search.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: graphmemory
Download link: https://github.com/bradAGI/GraphMemory/archive/main.zip#graphmemory

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.