# Claude Memory

> Use this tool when you need to store and retrieve conversational context, knowledge, and data across multiple interactions, enabling Claude to maintain a persistent memory of conversations, facts, and documents. It solves problems of contextual understanding and information recall, providing outputs such as relevant conversation history and related documents through a Python-based interface. Ideal for use cases where manual prompting is impractical, and continuous learning and memory are essential.

Canonical page: https://skillsregistry.net/skills/whenmoon-memory  
JSON: https://api.skillsregistry.net/v1/skills/whenmoon-memory

## Description

Memory MCP server that provides persistent memory capabilities for Claude Desktop, enabling storage and retrieval of conversations, facts, documents, and code snippets. Built with Python and sentence transformers, it features episodic and semantic memory domains, temporal decay modeling, and vector similarity search. Particularly valuable for users who want Claude to maintain context and knowledge across conversations without manual prompting.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/whenmoon-memory)
- **Repository:** <https://github.com/whenmoon-afk/claude-memory-mcp>

## 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": "whenmoon-memory"
    }
  }
}
```

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