# Hipporag Memory

How to use the HippoRAG MCP tools (retrieve, rag_qa, index, delete, index_stats) as...

- Repository: https://github.com/OSU-NLP-Group/HippoRAG (4089 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-10-06
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add OSU-NLP-Group/HippoRAG --skill hipporag-memory -g -a claude-code -y`
Codex: `npx skills add OSU-NLP-Group/HippoRAG --skill hipporag-memory -g -a codex -y`
Cursor: `npx skills add OSU-NLP-Group/HippoRAG --skill hipporag-memory -g -a cursor -y`
Gemini CLI: `npx skills add OSU-NLP-Group/HippoRAG --skill hipporag-memory -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add OSU-NLP-Group/HippoRAG`

## Description

How to use the HippoRAG MCP tools (retrieve, rag_qa, index, delete, index_stats) as long-term memory. Use when the user asks to remember, index or "add to memory" documents, notes or files, when they ask questions that may be answered by previously indexed material, or when they ask to forget or remove indexed content.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# HippoRAG long-term memory

The `hipporag` MCP server keeps a persistent knowledge-graph index on disk. Indexed passages survive across sessions and projects, so check it before saying you don't know something the user may have indexed earlier.

## Choosing a tool

- **`retrieve`**: the default for answering questions. It returns ranked passages with `source_id` and metadata and makes no LLM call. Read the passages, answer in your own words, and cite `source_id`s. Use `top_k` 5, 10 for most questions and up to ~20 for broad or multi-hop ones.
- **`rag_qa`**: only when the user explicitly wants HippoRAG's own answer, for example when comparing against the paper's QA pipeline. It costs an extra server-side LLM call, and you still need to check its answer against the returned passages.
- **`index_stats`**: check that the index is non-empty and see which LLM and embedding model it uses. Call it first when a retrieval fails or comes back empty.
- **`index`**: add documents (see below).
- **`delete`**: remove passages by `source_id` (preferred) or by exact passage text as returned by `retrieve`. Deletion cannot be undone, so confirm with the user before deleting anything they did not name explicitly.

## Indexing

The rest: https://github.com/OSU-NLP-Group/HippoRAG/blob/HEAD/plugins/hipporag/skills/hipporag-memory/SKILL.md