# minimem

> minimem — lelin1997-minimem. Use this tool when you need to manage and optimize AI agent memory, leveraging a four-layer memory pyramid and advanced technologies like Dream Engine and Karpathy Compile. It solves problems related to memory management, knowledge retention, and compilation, providing a centralized memory service for AI agents. With git capabilities, it accepts code repositories as input and outputs optimized memory configurations.

Canonical page: https://skillsregistry.net/skills/lelin1997-minimem  
JSON: https://api.skillsregistry.net/v1/skills/lelin1997-minimem

## Description

🧠 AI Agent 的中央记忆服务 — L1→L4四层记忆金字塔 + Dream Engine + Karpathy Compile + MCP协议

## 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:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/lelin1997/minimem)

## 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": "lelin1997-minimem"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lelin1997-minimem` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lelin1997-minimem/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