neo4j-agent-memory-skill

Name: neo4j-agent-memory-skill
Author: neo4j-contrib

368installs33forks

How to install neo4j-agent-memory-skill?

neo4j-contrib/neo4j-skills/neo4j-agent-memory-skill

$npx -y skills add neo4j-contrib/neo4j-skills --skill neo4j-agent-memory-skill

Installs into the current project.

Summary

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, contex

Files · 1

View on GitHub

SKILL.md

1	# neo4j-agent-memory
2
3	Authoritative reference for the `neo4j-agent-memory` Python package — a Neo4j Labs project that gives AI agents three distinct memory layers (short-term, long-term, reasoning) in a single knowledge graph.
4
5	> ⚠️ Verify authoritative state before writing. Version numbers, extras, tool counts, and API surface change between releases. The values in this skill reflect a specific point in time. Before publishing anything version-sensitive, confirm against PyPI (`https://pypi.org/project/neo4j-agent-memory/`) and the GitHub README (`https://github.com/neo4j-labs/agent-memory`). PyPI is the authoritative source for version numbers — never infer.
6
7	## When to Use
8
9	- Building AI agents that need persistent memory (short-term, long-term, reasoning traces) backed by Neo4j
10	- Using the `neo4j-agent-memory` Python package or the hosted NAMS service at memory.neo4jlabs.com
11	- Integrating agent memory with LangChain, PydanticAI, CrewAI, AWS Strands, Google ADK, OpenAI Agents, LlamaIndex, or Microsoft Agent Framework
12	- Writing documentation, tutorials, or positioning content about graph-native agent memory
13	- Comparing graph-native memory against vector-only approaches
14
15	## When NOT to Use
16
17	- Plain Neo4j driver connections (no memory layer needed) → use `neo4j-driver-python-skill`
18	- Writing or optimizing Cypher queries → use `neo4j-cypher-skill`
19	- GraphRAG retrieval pipelines → use `neo4j-graphrag-skill`
20
21	---
22
23	## Project at a Glance
24
25	\| Field \| Value \|
26	\|-------\|-------\|
27	\| Package \| `neo4j-agent-memory` \|
28	\| PyPI \| https://pypi.org/project/neo4j-agent-memory/ \|
29	\| GitHub \| https://github.com/neo4j-labs/agent-memory \|
30	\| Canonical docs \| https://neo4j.com/labs/agent-memory/ \|
31	\| Hosted service \| https://memory.neo4jlabs.com (NAMS — early-access, not yet documented on official project pages) \|
32	\| Hosted MCP endpoint \| https://memory.neo4jlabs.com/mcp (SSE, bearer auth) \|
33	\| License \| Apache-2.0 \|
34	\| Python \| 3.10+ \|
35	\| Neo4j \| 5.20+ (required for vector indexes) \|
36	\| Status \| Experimental (Neo4j Labs, community-supported) \|
37	\| Current version (at time of writing) \| 0.1.1 — always verify PyPI before citing \|
38
39	## What It Is (One Sentence)
40
41	A graph-native memory system for AI agents that stores conversations, builds knowledge graphs, and records agent reasoning — all as connected nodes in a single Neo4j database.
42
43	## Consumption Models
44
45	`neo4j-agent-memory` ships in two consumption models. They are the same underlying project — the differences are how you run it, how you authenticate, and what's managed for you.
46
47	\| Option \| What It Is \| When to Choose \|
48	\|--------\|------------\|----------------\|
49	\| Self-hosted library \| `pip install neo4j-agent-memory` + your own Neo4j (local / Docker / Aura). Full Python API, local MCP server, and framework integrations run in your process. \| Dev, on-prem data, custom extraction pipelines, full control, bringing your own embeddings / LLMs. \|
50	\| Hosted (NAMS) \| Managed service at `https://memory.neo4jlabs.com`. Per-workspace isolated Neo4j Aura database, REST API, remote MCP endpoint, web console. \| Zero-infra trials, sharing memory across agents / machines, demos, teams that don't want to run Neo4j. \|
51
52	> ⚠️ NAMS is reachable but not yet referenced in the GitHub README or `neo4j.com/labs/agent-memory/`. Treat it as early-access / soft-launched. Do not assert SLAs, pricing, or GA status in published content. See the Hosted Service (NAMS) section below for details.
53
54	## The Three Memory Types
55
56	The defining architectural feature. Every piece of content describing the project should lead with this trinity.
57
58	\| Memory Type \| Stores \| Color Convention \|
59	\|-------------\|--------\|------------------\|
60	\| Short-Term \| Conversation messages, session history, sequential message chains, metadata-filtered search, LLM-powered summaries \| Green (`#B2F2BB` / `#2F9E44`) \|
61	\| Long-Term \| Entities (people, places, orgs), preferences, facts, and the relationships between t

People who liked this also viewed

6 picks

Type

neo4j-agent-memory-skill

368installs33forks

View on GitHub

How to install neo4j-agent-memory-skill?

neo4j-contrib/neo4j-skills/neo4j-agent-memory-skill

$npx -y skills add neo4j-contrib/neo4j-skills --skill neo4j-agent-memory-skill

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# neo4j-agent-memory
2
3	Authoritative reference for the `neo4j-agent-memory` Python package — a Neo4j Labs project that gives AI agents three distinct memory layers (short-term, long-term, reasoning) in a single knowledge graph.
4
5	> ⚠️ Verify authoritative state before writing. Version numbers, extras, tool counts, and API surface change between releases. The values in this skill reflect a specific point in time. Before publishing anything version-sensitive, confirm against PyPI (`https://pypi.org/project/neo4j-agent-memory/`) and the GitHub README (`https://github.com/neo4j-labs/agent-memory`). PyPI is the authoritative source for version numbers — never infer.
6
7	## When to Use
8
9	- Building AI agents that need persistent memory (short-term, long-term, reasoning traces) backed by Neo4j
10	- Using the `neo4j-agent-memory` Python package or the hosted NAMS service at memory.neo4jlabs.com
11	- Integrating agent memory with LangChain, PydanticAI, CrewAI, AWS Strands, Google ADK, OpenAI Agents, LlamaIndex, or Microsoft Agent Framework
12	- Writing documentation, tutorials, or positioning content about graph-native agent memory
13	- Comparing graph-native memory against vector-only approaches
14
15	## When NOT to Use
16
17	- Plain Neo4j driver connections (no memory layer needed) → use `neo4j-driver-python-skill`
18	- Writing or optimizing Cypher queries → use `neo4j-cypher-skill`
19	- GraphRAG retrieval pipelines → use `neo4j-graphrag-skill`
20
21	---
22
23	## Project at a Glance
24
25	\| Field \| Value \|
26	\|-------\|-------\|
27	\| Package \| `neo4j-agent-memory` \|
28	\| PyPI \| https://pypi.org/project/neo4j-agent-memory/ \|
29	\| GitHub \| https://github.com/neo4j-labs/agent-memory \|
30	\| Canonical docs \| https://neo4j.com/labs/agent-memory/ \|
31	\| Hosted service \| https://memory.neo4jlabs.com (NAMS — early-access, not yet documented on official project pages) \|
32	\| Hosted MCP endpoint \| https://memory.neo4jlabs.com/mcp (SSE, bearer auth) \|
33	\| License \| Apache-2.0 \|
34	\| Python \| 3.10+ \|
35	\| Neo4j \| 5.20+ (required for vector indexes) \|
36	\| Status \| Experimental (Neo4j Labs, community-supported) \|
37	\| Current version (at time of writing) \| 0.1.1 — always verify PyPI before citing \|
38
39	## What It Is (One Sentence)
40
41	A graph-native memory system for AI agents that stores conversations, builds knowledge graphs, and records agent reasoning — all as connected nodes in a single Neo4j database.
42
43	## Consumption Models
44
45	`neo4j-agent-memory` ships in two consumption models. They are the same underlying project — the differences are how you run it, how you authenticate, and what's managed for you.
46
47	\| Option \| What It Is \| When to Choose \|
48	\|--------\|------------\|----------------\|
49	\| Self-hosted library \| `pip install neo4j-agent-memory` + your own Neo4j (local / Docker / Aura). Full Python API, local MCP server, and framework integrations run in your process. \| Dev, on-prem data, custom extraction pipelines, full control, bringing your own embeddings / LLMs. \|
50	\| Hosted (NAMS) \| Managed service at `https://memory.neo4jlabs.com`. Per-workspace isolated Neo4j Aura database, REST API, remote MCP endpoint, web console. \| Zero-infra trials, sharing memory across agents / machines, demos, teams that don't want to run Neo4j. \|
51
52	> ⚠️ NAMS is reachable but not yet referenced in the GitHub README or `neo4j.com/labs/agent-memory/`. Treat it as early-access / soft-launched. Do not assert SLAs, pricing, or GA status in published content. See the Hosted Service (NAMS) section below for details.
53
54	## The Three Memory Types
55
56	The defining architectural feature. Every piece of content describing the project should lead with this trinity.
57
58	\| Memory Type \| Stores \| Color Convention \|
59	\|-------------\|--------\|------------------\|
60	\| Short-Term \| Conversation messages, session history, sequential message chains, metadata-filtered search, LLM-powered summaries \| Green (`#B2F2BB` / `#2F9E44`) \|
61	\| Long-Term \| Entities (people, places, orgs), preferences, facts, and the relationships between t

People who liked this also viewed

6 picks

Type