# memos

> memos — markgatcha-memos. Use this tool when you need to persist and manage memory for AI agents and LLMs, solving data loss and inconsistency issues across sessions and deployments. Memos provides a universal local-first memory layer, allowing for seamless integration with git for version control and data management. It accepts various data inputs and outputs, making it a versatile solution for a range of AI applications.

Canonical page: https://skillsregistry.net/skills/markgatcha-memos  
JSON: https://api.skillsregistry.net/v1/skills/markgatcha-memos

## Description

MemOS - Universal local-first persistent memory layer for AI agents and LLMs

## Trust

- **Trust score (0–1):** 0.87
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/Markgatcha/memos)

## 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": "markgatcha-memos"
    }
  }
}
```

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