# Neo Memory

> Use this tool when you need to retain information across coding sessions, enable semantic recall, and establish relationships between memories. Neo Memory solves problems of data persistence and knowledge retention for AI agents, allowing them to learn and recall information without relying on external services. It takes in coding session data and outputs a graph-based memory structure, accessible via local ONNX embeddings.

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

## Description

Provides persistent memory for coding agents using an embedded KuzuDB graph database. Memories are stored as graph nodes with first-class relationships, enabling semantic recall via local ONNX embeddings without external services. Includes tools for remembering, recalling, connecting, exploring, and forgetting memories across sessions.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/oohiyorioo-neo-memory)
- **Repository:** <https://github.com/oohiyorioo/neo-memory-mcp>

## 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": "oohiyorioo-neo-memory"
    }
  }
}
```

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