# Graphiti Knowledge Graph

> Use this tool when you need to process and store complex, dynamic information with temporal relationships, and query it across conversations. It solves problems of information persistence and retrieval in applications with evolving data, such as conversational systems or dynamic knowledge bases. The Graphiti Knowledge Graph takes in text, messages, or JSON episodes and outputs a queryable graph of entities and relationships stored in Neo4j.

Canonical page: https://skillsregistry.net/skills/michabbb-graphiti  
JSON: https://api.skillsregistry.net/v1/skills/michabbb-graphiti

## Description

Built by michabbb as a working implementation of Graphiti's knowledge graph functionality, this server processes episodes (text, messages, or JSON) into nodes (entities) and facts (relationships) with temporal metadata stored in Neo4j. It supports dynamic information that evolves over time and includes custom entity extraction for requirements, preferences, and procedures. The implementation features Docker deployment, authentication via nonce tokens, background processing queues to prevent race conditions, making it valuable for applications that need persistent, queryable memory across conversations and complex data relationships.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/michabbb-graphiti)
- **Repository:** <https://github.com/michabbb/graphiti-mcp-but-working>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "michabbb-graphiti"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/michabbb-graphiti` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/michabbb-graphiti/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt