# Memory Graph

> Use this tool when you need to store and manage persistent knowledge graphs for AI assistants, solving problems of long-term memory persistence and contextual information retrieval. It provides a comprehensive interface for CRUD operations, search, and filtering, accepting entity-relationship models and observations as inputs and storing data in a configurable JSON file format. Ideal for AI applications requiring knowledge base management across conversation sessions.

Canonical page: https://skillsregistry.net/skills/memory-graph  
JSON: https://api.skillsregistry.net/v1/skills/memory-graph

## Description

This memory server implementation provides persistent knowledge graph storage for AI assistants through entity-relationship modeling with observations. Built with TypeScript and Hono.js, it offers both standard MCP protocol support and HTTP streaming capabilities, storing data in a configurable JSON file format with JSONL serialization. The implementation includes comprehensive CRUD operations for entities, relations, and observations, plus search and filtering capabilities, making it suitable for AI applications requiring long-term memory persistence, knowledge base management, and contextual information retrieval across conversation sessions.

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/memory-graph)
- **Repository:** <https://github.com/songlairui/mcp-memory-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": "memory-graph"
    }
  }
}
```

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