Neo4j Agent Memory Skill
Reference for the neo4j-agent-memory Python package: three-layer graph memory (short-term/long-term/reasoning) for AI agents.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 13, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 5599f12
Reproduced the package's exact async MemoryClient quickstart verbatim for a niche, likely post-cutoff API that a baseline attempt would otherwise have to guess at -- but the SKILL.md's 'combine with excalidraw / neo4j-styleguide / neo4j-labs-brand / diataxis' cross-references are all dead, none of those skills exist in this repo.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 3/5
- Triggers reliably 5/5
- Output vs. baseline 9/10
- Docs & honesty 3/5
What Neo4j Agent Memory Skill does
An authoritative reference for the neo4j-agent-memory Python package and its hosted NAMS service, covering the MemoryClient/MemorySettings API, the POLE+O entity model, the bundled MCP server, and integrations with LangChain, PydanticAI, CrewAI, AWS Strands, Google ADK, and other agent frameworks. Triggers on any mention of neo4j-agent-memory, graph-native agent memory, context graphs, POLE+O, or NAMS, and also when writing docs/positioning content that compares graph-native memory to vector-only approaches.
How to install Neo4j Agent Memory Skill
git clone https://github.com/neo4j-contrib/neo4j-skills
cd neo4j-skills
mkdir -p ~/.claude/skills
cp -r neo4j-agent-memory-skill ~/.claude/skills/neo4j-agent-memory-skill
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Neo4j Agent Memory Skill
-
/neo4j-agent-memory-skillReference for the neo4j-agent-memory Python package: three-layer graph memory (short-term/long-term/reasoning) for AI agents.
It also activates on plain-language prompts like these:
-
Set up neo4j-agent-memory for my AI agent -
Add graph-native memory to my LangChain agent -
How do I use the MemoryClient API in neo4j?
Frequently asked questions
- Is the Neo4j Agent Memory Skill skill free?
- Yes. The skill itself is free from neo4j-contrib/neo4j-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Neo4j Agent Memory Skill work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Works with setup. Reproduced the package's exact async MemoryClient quickstart verbatim for a niche, likely post-cutoff API that a baseline attempt would otherwise have to guess at -- but the SKILL.md's 'combine with excalidraw / neo4j-styleguide / neo4j-labs-brand / diataxis' cross-references are all dead, none of those skills exist in this repo.
- What is the Neo4j Agent Memory Skill SkillProof Score?
- 8.0/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 3/5.
- How do I install Neo4j Agent Memory Skill?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Neo4j Agent Memory Skill with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.