# mie

> mie — kraklabs-mie. Use this tool when you need to retain knowledge and context across multiple AI sessions and interactions. The mie persistent memory graph solves the problem of knowledge loss between sessions, allowing AI agents to recall facts, decisions, entities, and relationships. It accepts inputs from various AI providers, including Claude, Cursor, and ChatGPT, and outputs a unified knowledge graph that can be accessed via any MCP client.

Canonical page: https://skillsregistry.net/skills/kraklabs-mie  
JSON: https://api.skillsregistry.net/v1/skills/kraklabs-mie

## Description

Persistent memory graph for AI agents. Facts, decisions, entities, and relationships that survive across sessions, tools, and providers. MCP server — works with Claude, Cursor, ChatGPT, and any MCP client.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** AGPL-3.0
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/kraklabs/mie)

## 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": "kraklabs-mie"
    }
  }
}
```

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