neo4j-labsneo4j-labsOfficial·3 Agent Skills Included

agent-memory

Graph-backed persistent memory for conversations and knowledge

Stores conversations, entities, preferences, and reasoning traces in a Neo4j knowledge graph. Extracts and deduplicates entities automatically, eliminating manual context management and lost chat history. Ships Python and TypeScript SDKs plus an MCP server so agents recall past decisions across sessions and frameworks.
npx skills add neo4j-labs/agent-memory --all -g -y
Available:

Explains the repository's dual Python and TypeScript SDK layout, build commands, and memory architecture so the agent can navigate, test, and modify the codebase correctly.

All Skills in This Repository (3)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install agent-memory?

Run `npx skills add neo4j-labs/agent-memory --all -g -y` in your terminal to install all skills in this suite globally.

What does Neo4j Agent Memory do?

It gives AI agents persistent memory backed by a Neo4j knowledge graph, storing conversations, entities, preferences, and reasoning traces across sessions.

Does it work with Claude Desktop and Cursor?

Yes. It includes an MCP server with 16 tools that plugs into Claude Desktop, Claude Code, Cursor, and VS Code Copilot with zero code.

Which frameworks does it integrate with?

It provides ready-made integrations for LangChain, LlamaIndex, Pydantic AI, CrewAI, Google ADK, Strands, and the OpenAI Agents SDK.

Do I need to run my own Neo4j database?

No. You can use the hosted NAMS service with just an API key, or point the SDK at your own Neo4j instance for full control.

Related Repositories in Software Engineering

View All in Software Engineering