GraphMemory
GraphMemory is a AI agent skill for database and sql tools, published by bradAGI.
Vector + full-text search, GraphRAG retrieval, merge/upsert, graph traversal, and visualization — all in one Python package powered by DuckDB.
Is it any good?
Effectiveness · benchmark pending
We haven't benchmarked GraphMemory yet, so its score is provisional — computed from safety, maintenance, and documentation only, with popularity given no weight. When we benchmark it, we measure whether it produces materially better output than a frontier model alone, and that result leads the score. How we measure.
About GraphMemory
Description · AI-summarised from the bradAGI README
GraphMemory is an embedded graph database designed for RAG and knowledge graph applications. It provides vector similarity search (HNSW-indexed with L2, cosine, inner product metrics), full-text BM25 search, hybrid search combining both, and a complete GraphRAG retrieval pipeline with graph expansion and context assembly. Features include node and edge merge/upsert with deduplication, fluent query builder with multi-hop traversal, optional DSPy-based entity/relationship extraction, NetworkX graph algorithms (PageRank, centrality, components), import/export (JSON, CSV, GraphML), and an interactive D3.js browser visualizer. Thread-safe with connection pooling, transactions, and automatic retry with exponential backoff.
Where it fits
Browse related skills
Install GraphMemory
Install
Install via agent tool
# install via agent tool
# see vendor docsInstall with your AI
Zero install · paste into ChatGPT, Claude, Cursor…
Install the "GraphMemory" skill into my project by following all instructions at https://skillsdirectory.co/s/bradagi-graphmemory
Your assistant reads /s/bradagi-graphmemory and follows it — fetching the files from the source, placing them, and confirming before it runs anything. No account needed. How this works.
Frequently asked
FAQ
What does GraphMemory do?
Vector + full-text search, GraphRAG retrieval, merge/upsert, graph traversal, and visualization — all in one Python package powered by DuckDB.
How do I install GraphMemory?
GraphMemory is a AI agent skill. Primary install path: # install via agent tool # see vendor docs
What is the Skill Score for GraphMemory?
GraphMemory has a Skill Score of 6.1/10 (Solid). It is currently a provisional score — GraphMemory hasn't been benchmarked yet, so it weights safety 75/100 (40%), maintenance 50/100 (30%), and documentation 70/100 (30%). Popularity carries zero weight until effectiveness is measured. See methodology.
Is GraphMemory free?
GraphMemory is published under the MIT license. See the vendor's source repository for any usage limits or paid tiers.
Related skills in Database and SQL tools
Related
Supabase MCP
Connects Supabase projects to Cursor, Claude, Windsurf, and other AI assistants for natural-language database, schema, and project operations.
Neon MCP Server
Official MCP server for the Neon serverless Postgres platform — manage projects, branches, and databases through the Neon Management API.
Anyquery
Anyquery is a SQL query engine that lets AI agents and users query files, databases, web apps, and local services using SQL, with built-in MCP support for Claude and other LLMs.
Embed this score
For maintainers · always-current, links back
Put it in your README — it updates as the score changes.[](https://skillsdirectory.co/skills/bradagi-graphmemory)
<a href="https://skillsdirectory.co/skills/bradagi-graphmemory"><img src="https://skillsdirectory.co/badge/bradagi-graphmemory.svg" alt="Scored by skillsdirectory" height="28" /></a>