# pangu

> pangu — mlte0907-pangu. Use this tool when you need to implement a local, prioritized AI long-term memory service that can forget, associate, and consolidate information. It solves problems related to AI memory management, providing a simple setup process through a single command and offering multiple interfaces, including MCP, REST, and Web UI. Ideal for use cases where independent, local AI memory management is required, with optional integration with git for version control.

Canonical page: https://skillsregistry.net/skills/mlte0907-pangu  
JSON: https://api.skillsregistry.net/v1/skills/mlte0907-pangu

## Description

本地优先的 AI 长期记忆服务：会遗忘、会联想、会巩固。MCP + REST + Web UI，一条命令装好；不用 DSH 也能独立使用。

## Trust

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

## 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/Mlte0907/pangu)

## 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": "mlte0907-pangu"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mlte0907-pangu` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mlte0907-pangu/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