# claude-memory

> claude-memory — hiromiogawa-claude-memory. Use this tool when you need to implement a long-term memory system for Claude Code, enabling cross-session memory retrieval through hybrid search using pgvector and pg_bigm. It solves problems of data persistence and retrieval across multiple sessions, providing a robust interface for storing and querying data. Ideal for use cases requiring seamless data recall and analysis, such as git-based version control and knowledge management.

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

## Description

Claude Code 向けの長期記憶システム — セッションを跨いだ記憶をハイブリッド検索（pgvector + pg_bigm）で提供

## Trust

- **Trust score (0–1):** 0.87
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/hiromiogawa/claude-memory)

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

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