# hybrid-rag-memory

> hybrid-rag-memory — masaki-kato-119-hybrid-rag-memory. Use this tool when you need to enhance AI agents' memory and retrieval capabilities, solving problems of information overload and knowledge retention by leveraging a hybrid dense+sparse RAG system with tag-based long-term memory. It accepts document inputs and produces ranked search results, enabling efficient document ingestion, search, and index management. Ideal for use cases requiring advanced knowledge management and information retrieval, such as question answering and text analysis.

Canonical page: https://skillsregistry.net/skills/masaki-kato-119-hybrid-rag-memory  
JSON: https://api.skillsregistry.net/v1/skills/masaki-kato-119-hybrid-rag-memory

## Description

Enables AI agents to use a hybrid dense+sparse RAG system with tag-based long-term memory (importance, knowledge-type decay, access-frequency boost) via MCP tools for document ingestion, hybrid search, staged reranking, forgetting, and index management.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** scanned
- **Last scanned:** 2026-09-04

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/htvatkc2bm)
- **Repository:** <https://github.com/masaki-kato-119/hybrid-rag-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": "masaki-kato-119-hybrid-rag-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/masaki-kato-119-hybrid-rag-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/masaki-kato-119-hybrid-rag-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