# mnemon

> mnemon — nousergon-mnemon. Use this tool when you need to store and retrieve long-term memory for AI agents across multiple devices, solving problems of data fragmentation and third-party dependency. It provides a self-hosted, cross-device memory vault with hybrid semantic and keyword search functionality, taking input from various MCP clients and outputting relevant data. Use mnemon in contexts where secure, decentralized data management is crucial, such as AI model training or knowledge graph construction.

Canonical page: https://skillsregistry.net/skills/nousergon-mnemon  
JSON: https://api.skillsregistry.net/v1/skills/nousergon-mnemon

## Description

Self-hosted, cross-device long-term memory for AI agents via MCP — one vault shared across any MCP client (Claude, Cursor, Gemini CLI, and more). Hybrid semantic + keyword search, your keys, no third-party auth vendor. pip install mnemon-memory

## Trust

- **Trust score (0–1):** 0.24
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/nousergon/mnemon)

## 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": "nousergon-mnemon"
    }
  }
}
```

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