# Graphiti

> Use this tool when you need to store, retrieve, and reason about complex relationships between entities over time. Graphiti solves problems like tracking user preferences, documenting procedures, and maintaining factual relationships that change over time, by providing a temporal knowledge graph system with semantic and keyword search capabilities. It accepts inputs like conversations, documents, and entities, and outputs relevant facts and relationships with temporal context.

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

## Description

The Graphiti MCP server provides AI assistants with access to a temporal knowledge graph system for storing, retrieving, and reasoning about relationships between entities. Built by Zep Software, this implementation uses Neo4j as its database backend and supports various LLM providers including OpenAI, Anthropic, and Google. The server exposes tools for adding episodes (conversations or documents), extracting entities and relationships, searching the graph with semantic and keyword matching, and retrieving facts with temporal context. It's particularly valuable for applications requiring persistent memory across conversations, such as tracking user preferences, documenting procedures, or maintaining factual relationships that change over time.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/zep-graphiti)
- **Repository:** <https://github.com/getzep/graphiti/tree/HEAD/mcp_server>

## 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": "zep-graphiti"
    }
  }
}
```

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