neo4j-memory

Neo4j-memory is a tool that allows AI to remember past conversations long-term.

  • AI
  • Databases
Neo4j-memory is a tool that allows AI to remember past conversations long-term. It saves information in a structured graph database, similar to how a human brain connects ideas. This ensures your AI stays personalised, providing relevant answers based on your previous interactions and unique preferences.

Platform availability

Available on 0 of 10 platforms

  • Unraid (not listed)
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

51/100 Fair

Maintained
84last commit 15 days ago
Popular
3767 GitHub stars
Easy to install
250 install platforms, install notes, Docker image
Light to run
602 GB minimum RAM, runs on ARM
Security check
201 serious finding, 9 minor, CI, tests
GitHub stars
67
Open issues
3
Last commit
2026-11-06
License
MIT
Activity
declining

Checked 4 days ago - source: GitHub (knowall-ai/mcp-neo4j-agent-memory)

Resources & Compatibility

Minimum requirements: 2 GB RAM. ARM (e.g. Raspberry Pi) is supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Getting started This MCP (Model Context Protocol) server runs as the mcp/neo4j-memory Docker image and connects to a Neo4j database. Register it with a compatible client such as Claude Desktop or Cursor to give the agent persistent graph memory. source

Fetched 41 days ago - each note links to its source

Alternatives (3)

  • Graph Commons
  • Kumu
  • neo4j - Neo4j is a graph database for developers to store, query, and traverse interconnected data as nodes and relationships in high-performance a…

Checked 40 days ago - source: AlternativeTo

Common questions

How do I point Reverie at my self-hosted Neo4j instance?

Set NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD, and NEO4J_DATABASE in the MCP server environment. The provided example uses a local Bolt URI on port 7687.

Can I use local embeddings instead of sending data to an external AI provider?

Yes. Reverie uses local embeddings by default, so no API key is needed. It can also be switched to OpenAI, Azure OpenAI, Ollama, or Voyage.

How do I reduce duplicate or messy entity nodes over time?

Run the dream tool as a scheduled job. It merges duplicates safely, canonicalises labels, re-embeds, counts orphans, and flags nodes that have become property dumps.

Can multiple agents share the same memory graph?

Yes. Reverie is an MCP server, so any Model Context Protocol client can use the same graph. A Hermes Agent memory-provider flavour is also available.

Which package and repository should I use if I have the old mcp-neo4j-agent-memory setup?

Use the npm package @knowall-ai/reverie, which is the successor to @knowall-ai/mcp-neo4j-agent-memory. The GitHub repository is knowall-ai/mcp-reverie, and old URLs redirect.

Answers sourced from github.com

Community

Collected 48 days ago - public community threads