# fuga-memory

> fuga-memory — densuke-fuga-memory. Use this tool when you need to enhance the long-term memory of Large Language Models (LLMs) with efficient storage and retrieval of information. It solves problems of knowledge retention and recall for AI assistants by providing a hybrid search functionality with time-decay scoring. The fuga-memory tool takes in data to be stored and retrieves relevant information based on search queries, making it ideal for applications requiring persistent memory and information recall across multiple AI assistants.

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

## Description

An MCP server providing long-term memory for LLMs via hybrid search (FTS5 + vector) stored in SQLite, with time-decay scoring and support for multiple AI assistants.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gp2vt4m30g)
- **Repository:** <https://github.com/densuke/fuga-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": "densuke-fuga-memory"
    }
  }
}
```

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