# leafmem

> leafmem — xdragonjia-leafmem. Use this tool when you need to provide AI agents with persistent and scoped memory for efficient information retrieval and storage. LeafMem solves problems related to contextual understanding and knowledge retention by capturing turns, storing memories, and building recall context. It accepts input from AI interactions and outputs relevant memories and recall context, making it ideal for use cases requiring local retrieval and embedding rerank.

Canonical page: https://skillsregistry.net/skills/xdragonjia-leafmem  
JSON: https://api.skillsregistry.net/v1/skills/xdragonjia-leafmem

## Description

MCP server for LeafMem, a layered memory engine that gives AI agents persistent, scoped memory with local retrieval and optional embedding rerank. It exposes tools for capturing turns, storing memories, and building recall context.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/b31itr26kv)
- **Repository:** <https://github.com/xdragonjia/leafmem>

## 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": "xdragonjia-leafmem"
    }
  }
}
```

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