Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model, MemoryClient/MemorySettings, the memory MCP server, or any of the framework integrations (LangChain, PydanticAI, CrewAI, AWS Strands, Google ADK, Microsoft Agent Framework, OpenAI Agents, LlamaIndex). Also use when the user mentions the hosted service at memory.neo4jlabs.com, NAMS, the Neo4j Agent Memory Service, the nams API key prefix, or the hosted MCP endpoint. Also use when writing documentation, blog posts, tutorials, PRDs, or code samples for the project, when comparing agent memory approaches, or when positioning graph-native memory against vector-only approaches — even if the user doesn't explicitly name the package.
EnglishManages Neo4j Aura Agents via the v2beta1 REST API — create, list, get, update,…
EnglishUse when importing unstructured or semi-structured content into Neo4j as a knowledge graph: PDF, HTML, plain text, or JSON documents; chunking strategies; entity and relationship extraction with LLMs (SimpleKGPipeline, LLM Graph Builder); apoc.load.json for JSON ingestion; or LangChain/LlamaIndex document loaders targeting Neo4j. Does NOT handle structured CSV/relational imports — use neo4j-import-skill. Does NOT handle GraphRAG retrieval pipelines — use neo4j-graphrag-skill. Does NOT handle vector index setup — use neo4j-vector-search-skill.
EnglishComprehensive guide to using the official Neo4j .NET Driver (v6, current stable) —…
EnglishComprehensive guide to using the official Neo4j Go Driver (v6, current stable) —…
EnglishComprehensive guide to using the official Neo4j Java Driver (v6, current stable) —…
EnglishComprehensive guide to using the official Neo4j Python Driver (v6, current stable) —…
EnglishOrchestrates the full journey from zero to a running Neo4j application. Executes 8 named stages in order: prerequisites → context → provision → model → load → explore → query → build. Each stage has its own reference file in references/ that the agent reads and follows when entering that stage. Supports both HITL and fully autonomous operation. Time budget: ≤15 min after DB is running (autonomous), ≤90 min total (HITL).
EnglishUse when importing structured data into Neo4j: LOAD CSV, UNWIND + CALL IN TRANSACTIONS batch upserts, neo4j-admin import (offline bulk load), apoc.load.csv/json for relational-to-graph migrations, or verifying import counts and constraints. Does NOT handle unstructured document / PDF / JSON chunking pipelines — use neo4j-document-import-skill. Does NOT handle live application write queries — use neo4j-cypher-skill. Does NOT handle neo4j-admin CLI flags — use neo4j-cli-tools-skill.
EnglishMigrates Neo4j driver code and Cypher queries from older versions (4.x,…
EnglishUse when designing or reviewing a Neo4j graph data model: choosing node labels and relationship types, deciding what to embed vs reference, normalizing or denormalizing for traversal performance, reviewing a schema against graph modeling best practices, or migrating a relational/document schema to a graph. Does NOT handle Cypher query writing — use neo4j-cypher-skill. Does NOT handle application-side mapping (Spring Data Neo4j OGM, GraphQL type definitions) — use neo4j-spring-data-skill or neo4j-graphql-skill.
EnglishNeo4j Visualization Library (NVL) — framework-agnostic graph rendering for the browser.
EnglishDiagnoses and fixes slow Neo4j Cypher queries by reading execution plans,…
EnglishProgrammatic security management in Neo4j — RBAC/ABAC, user lifecycle (CREATE/ALTER/DROP…
EnglishUse when reading from or writing to Neo4j with Apache Spark or Databricks using…
EnglishUse when building Spring Boot applications with Neo4j using Spring Data Neo4j (SDN): @Node entity mapping, @Relationship, Neo4jRepository, ReactiveNeo4jRepository, @Query annotations, application.yml configuration, projections, or Neo4j-OGM. Also covers Spring AI Neo4jVectorStore integration. Does NOT handle raw Java driver code (no Spring) — use neo4j-driver-java-skill. Does NOT handle Cypher query authoring — use neo4j-cypher-skill. Does NOT handle driver version upgrades — use neo4j-migration-skill.
EnglishServerless GDS sessions on Neo4j Aura — covers GdsSessions,…
UncertainComprehensive guide to using the official Neo4j JavaScript/TypeScript Driver (v6) —…
LatinRun Neo4j Graph Analytics algorithms (PageRank, Louvain, WCC, Dijkstra,…
Latin
AGENT SKILLS ATLASIncludes Neo4j Agent Memory Skill, Neo4j Aura Agent Skill, Neo4j Document Import Skill, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Neo4j Agent Memory Skill
Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model, MemoryClient/MemorySettings, the memory MCP server, or any of the framework integrations (LangChain, PydanticAI, CrewAI, AWS Strands, Google ADK, Microsoft Agent Framework, OpenAI Agents, LlamaIndex). Also use when the user mentions the hosted service at memory.neo4jlabs.com, NAMS, the Neo4j Agent Memory Service, the nams API key prefix, or the hosted MCP endpoint. Also use when writing documentation, blog posts, tutorials, PRDs, or code samples for the project, when comparing agent memory approaches, or when positioning graph-native memory against vector-only approaches — even if the user doesn't explicitly name the package.
Neo4j Aura Agent Skill
Manages Neo4j Aura Agents via the v2beta1 REST API — create, list, get, update, delete,
Neo4j Document Import Skill
Use when importing unstructured or semi-structured content into Neo4j as a knowledge graph: PDF, HTML, plain text, or JSON documents; chunking strategies; entity and relationship extraction with LLMs (SimpleKGPipeline, LLM Graph Builder); apoc.load.json for JSON ingestion; or LangChain/LlamaIndex document loaders targeting Neo4j. Does NOT handle structured CSV/relational imports — use neo4j-import-skill. Does NOT handle GraphRAG retrieval pipelines — use neo4j-graphrag-skill. Does NOT handle vector index setup — use neo4j-vector-search-skill.
Neo4j Driver Dotnet Skill
Comprehensive guide to using the official Neo4j .NET Driver (v6, current stable) — covering
Neo4j Driver Go Skill
Comprehensive guide to using the official Neo4j Go Driver (v6, current stable) — covering
Neo4j Driver Java Skill
Comprehensive guide to using the official Neo4j Java Driver (v6, current stable) — covering
Neo4j Driver Python Skill
Comprehensive guide to using the official Neo4j Python Driver (v6, current stable) — covering
Neo4j Getting Started Skill
Orchestrates the full journey from zero to a running Neo4j application. Executes 8 named stages in order: prerequisites → context → provision → model → load → explore → query → build. Each stage has its own reference file in references/ that the agent reads and follows when entering that stage. Supports both HITL and fully autonomous operation. Time budget: ≤15 min after DB is running (autonomous), ≤90 min total (HITL).
Neo4j Import Skill
Use when importing structured data into Neo4j: LOAD CSV, UNWIND + CALL IN TRANSACTIONS batch upserts, neo4j-admin import (offline bulk load), apoc.load.csv/json for relational-to-graph migrations, or verifying import counts and constraints. Does NOT handle unstructured document / PDF / JSON chunking pipelines — use neo4j-document-import-skill. Does NOT handle live application write queries — use neo4j-cypher-skill. Does NOT handle neo4j-admin CLI flags — use neo4j-cli-tools-skill.
Neo4j Kafka Skill
Configure and operate the Neo4j Connector for Kafka (sink + source) and the
Neo4j Migration Skill
Migrates Neo4j driver code and Cypher queries from older versions (4.x, 5.x)
Neo4j Modeling Skill
Use when designing or reviewing a Neo4j graph data model: choosing node labels and relationship types, deciding what to embed vs reference, normalizing or denormalizing for traversal performance, reviewing a schema against graph modeling best practices, or migrating a relational/document schema to a graph. Does NOT handle Cypher query writing — use neo4j-cypher-skill. Does NOT handle application-side mapping (Spring Data Neo4j OGM, GraphQL type definitions) — use neo4j-spring-data-skill or neo4j-graphql-skill.
Neo4j Nvl Skill
Neo4j Visualization Library (NVL) — framework-agnostic graph rendering for the browser.
Neo4j Query Tuning Skill
Diagnoses and fixes slow Neo4j Cypher queries by reading execution plans, identifying
Neo4j Security Skill
Programmatic security management in Neo4j — RBAC/ABAC, user lifecycle (CREATE/ALTER/DROP USER),
Neo4j Spark Skill
Use when reading from or writing to Neo4j with Apache Spark or Databricks using the
Neo4j Spring Data Skill
Use when building Spring Boot applications with Neo4j using Spring Data Neo4j (SDN): @Node entity mapping, @Relationship, Neo4jRepository, ReactiveNeo4jRepository, @Query annotations, application.yml configuration, projections, or Neo4j-OGM. Also covers Spring AI Neo4jVectorStore integration. Does NOT handle raw Java driver code (no Spring) — use neo4j-driver-java-skill. Does NOT handle Cypher query authoring — use neo4j-cypher-skill. Does NOT handle driver version upgrades — use neo4j-migration-skill.
Neo4j Aura Graph Analytics Skill
Serverless GDS sessions on Neo4j Aura — covers GdsSessions, AuraAPICredentials,
Neo4j Driver JavaScript Skill
Comprehensive guide to using the official Neo4j JavaScript/TypeScript Driver (v6) — covering
Neo4j Gds Skill
Neo4j Graph Data Science (GDS) plugin — graph projection, algorithm execution,
Neo4j Genai Plugin Skill
Use Neo4j GenAI Plugin ai.text. functions and procedures for in-Cypher
Neo4j Snowflake Graph Analytics Skill
Run Neo4j Graph Analytics algorithms (PageRank, Louvain, WCC, Dijkstra, KNN,
Neo4j Vector Index Skill
Create and manage Neo4j vector indexes, run vector similarity search (ANN/kNN),
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Neo4j Agent Memory Skill skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.