# Claude Memory

> Use this tool when you need to store and retrieve long-term memory for AI conversations, solving problems of lost context and accumulated knowledge across multiple interactions. It takes in conversation data and outputs categorized and searchable information, utilizing full-text and semantic search capabilities. Ideal for use cases requiring persistent memory management, such as maintaining conversational history and context across sessions.

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

## Description

Claude Memory Server provides persistent long-term memory storage for AI conversations using SQLite database with full-text search and optional semantic search capabilities through Ollama embeddings. The implementation offers comprehensive memory management tools including storage, retrieval, categorization, and similarity-based search across predefined categories like facts, preferences, conversations, and projects, with support for hybrid text and semantic search algorithms using cosine similarity. Built with TypeScript and the Model Context Protocol SDK, it includes an optional memory hook script for automatically capturing important information from Claude sessions, making it valuable for users who want to maintain context and accumulated knowledge across multiple AI interactions without losing conversational history.

## 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:** database
- **Updated:** 2026-09-01

## Source

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

## 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": "xiy-claude-memory"
    }
  }
}
```

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