# pamie

> pamie — kurocho-pamie. Use this tool when you need to retain long-term memory for AI agents like Copilot, Claude, and Codex, enabling them to recall previous interactions and learn from experience. It solves the problem of knowledge retention and continuity, allowing for more informed and personalized responses. With git integration, pamie provides a self-hosted solution for storing and retrieving agent memory, making it ideal for use cases requiring data privacy and control.

Canonical page: https://skillsregistry.net/skills/kurocho-pamie  
JSON: https://api.skillsregistry.net/v1/skills/kurocho-pamie

## Description

Self-hosted long-term memory for Copilot, Claude, Codex agents with MCP

## Trust

- **Trust score (0–1):** 0.90
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/kurocho/pamie)

## 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": "kurocho-pamie"
    }
  }
}
```

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