SkillAgentSearch skills...

AutoRAG

Your Personal Librarian Agent. Ask anything on your computer, organize files, remember important info and files.

Install / Use

claude mcp add Marker-Inc-Korea -- npx -y github:Marker-Inc-Korea/AutoRAG

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

84/100

Supported Platforms

Claude Code
Claude Desktop

Tags

Our assessment of AutoRAG

AutoRAG scores 84/100 on our quality scale, 626th of 947 AI & Machine Learning skills we index.

Its MCP Server is 61 KB long, well organised into 53 sections with 24 code examples: long enough that it reads more like full documentation than a focused instruction file, which agents can find harder to follow.

With 5,897 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
21/30
Structure
20/20
Description
12/15
Adoption
16/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated today, so AutoRAG is actively maintained.
  • Our last check on 2026-11-13 found the source still online.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-11-11. Automated pattern scan on 2026-11-11. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

AutoRAG compared with similar skills

All 4 of these similar skills score higher than AutoRAG; compare them before choosing.

SkillScoreStarsUpdatedFormat
AutoRAG (this skill)by Marker-Inc-Korea845.9ktodayMCP Server
claude-memby thedotmack100117.6ktodayCLAUDE.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
Understand-Anythingby Egonex-AI10092.8k1d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md

Frequently asked questions

How do I install AutoRAG?
Run claude mcp add Marker-Inc-Korea -- npx -y github:Marker-Inc-Korea/AutoRAG. The install tabs above show the steps for each supported agent.
Which AI agents does AutoRAG work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is AutoRAG safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is AutoRAG still maintained?
The repository was last updated today, so AutoRAG is actively maintained.

AutoRAG Agent

Now your agent can find anything in your computer.

<p align="left"> <a href="https://www.npmjs.com/package/@autorag/librarian"><img src="https://img.shields.io/npm/v/@autorag/librarian.svg?style=flat-square&color=38bdf8" alt="npm version" /></a> <a href="https://www.npmjs.com/package/@autorag/librarian"><img src="https://img.shields.io/npm/dm/@autorag/librarian.svg?style=flat-square&color=818cf8" alt="npm downloads" /></a> <a href="https://github.com/Marker-Inc-Korea/AutoRAG/stargazers"><img src="https://img.shields.io/github/stars/Marker-Inc-Korea/AutoRAG?style=flat-square&logo=github&color=f59e0b" alt="GitHub stars" /></a> <a href="https://github.com/Marker-Inc-Korea/AutoRAG/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/Marker-Inc-Korea/AutoRAG/ci.yml?branch=main&label=CI&style=flat-square" alt="CI Status" /></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache--2.0-green.svg?style=flat-square" alt="License: Apache-2.0" /></a> <img src="https://img.shields.io/badge/node-%3E%3D24.0.0-informational.svg?style=flat-square" alt="Node >= 24" /> <img src="https://img.shields.io/badge/bun-%3E%3D1.2-black.svg?style=flat-square&logo=bun" alt="Bun >= 1.2" /> </p> <p align="center"> <img src="assets/autorag-agent-social-preview.png" alt="AutoRAG Agent" width="100%" /> </p>

[!IMPORTANT] Looking for the original AutoRAG (RAG AutoML / pipeline optimization tool)? This repository now hosts AutoRAG 2.0, a complete reimagining of AutoRAG as a personal librarian agent for your office work. The original Python-based AutoRAG — the RAG AutoML tool for automatically finding an optimal RAG pipeline for your data — now lives in the legacy/ directory of this repository.

The legacy AutoRAG is NOT abandoned. It continues to be maintained (bug fixes, dependency updates, and PyPI releases via pip install AutoRAG) in maintenance mode. Existing users can keep using it exactly as before — see the legacy README for its documentation, and file issues in this repository as usual. New feature development is focused on AutoRAG Agent (2.0).


🖥️ The desktop app

A Finder for your computer that understands what's inside your files. The AutoRAG desktop app puts this librarian behind a real file manager: browse your folders as usual, then ask a question and get an answer that cites the files, chats, and mail it came from. Everything it searches with is the engine in this repository.

<p align="center"> <img src="assets/app/finder.webp" alt="AutoRAG desktop app: a folder in list view with a version stack expanded and the index column" width="100%" /> </p> <table> <tr> <td width="50%" valign="top">

🔎 Just ask

Ask the way you'd ask a teammate. The librarian reads the files and writes back, every claim linked to the passage behind it. Drag files, folders, or links into a question to ask about just those.

</td> <td width="50%" valign="top"> <img src="assets/app/ask.webp" alt="An answer about the Seoul office lease with numbered citations" /> </td> </tr> <tr> <td width="50%" valign="top"> <img src="assets/app/versions.webp" alt="A folder in list view with document versions stacked under one row" /> </td> <td width="50%" valign="top">

🗂️ Spot the twins

proposal-final, proposal-v3, proposal (1): stacked into one row, newest on top, tagged Latest, Similar, or Identical. Powered by dupey, the same scan as autorag duplicates.

</td> </tr> <tr> <td width="50%" valign="top">

⌨️ Space to see anything

Markdown, code, PDF, video, audio, Office, and HWP/HWPX previewed instantly in Quick Look. HWP pages are drawn locally by rhwp; Hancom Office is not required.

</td> <td width="50%" valign="top"> <img src="assets/app/quick-look.webp" alt="Quick Look showing a multi-page PDF with a page rail" /> </td> </tr> <tr> <td width="50%" valign="top"> <img src="assets/app/panes.webp" alt="Two folder panes side by side, each with its own tabs" /> </td> <td width="50%" valign="top">

🪟 A real file manager

Tabs and split panes: drag a tab to an edge to split, and every pane keeps its own tabs, so a folder and a conversation sit side by side. Folders update live as other apps change them.

</td> </tr> </table>

And more: hybrid keyword + meaning search with a reranker · scheduled re-indexing that runs even while the app is closed · an Ask entry in the Finder and Explorer right-click menu · light and dark mode · Korean, English, Japanese, and Simplified Chinese.

Every place, one search

The app connects the same datasources the librarian does, and searches them right alongside your files:

<table> <tr> <td align="center" width="25%">💬<br><b>Slack</b><br>Channels and threads</td> <td align="center" width="25%">💛<br><b>KakaoTalk</b><br>Chats on this computer</td> <td align="center" width="25%">🎮<br><b>Discord</b><br>Servers and forums</td> <td align="center" width="25%">✈️<br><b>Telegram</b><br>Chats and channels</td> </tr> <tr> <td align="center">📱<br><b>WhatsApp</b><br>Messages, read-only</td> <td align="center">✉️<br><b>Mail</b><br>Every inbox you sign in to</td> <td align="center">🐙<br><b>GitHub</b><br>Repos, issues, PRs</td> <td align="center">🔮<br><b>Obsidian</b><br>Your vaults</td> </tr> </table>

Private by design

  • Embedded on your machine. Semantic indexing runs on MinSync's local Qwen3-Embedding-0.6B engine (1024 dimensions), which MinSync provisions and runs; AutoRAG owns no embedding model. File contents are never sent to a remote embedder unless you explicitly configure a remote minSync.embedder.
  • Keys stay encrypted. Sign-in tokens and API keys live in the system's encrypted store, never in a config file.
  • Bring your own model. Use the hosted Dazzi Models plan, or connect your own provider key and pay the provider directly.

[!TIP] The Dazzi desktop app's source lives in NomaDamas/AutoRAG-app (Electron + React, Fair Source under FSL-1.1-MIT). It depends on the open-source @autorag/librarian engine (Apache-2.0) from this repository; build, run, and file app issues there.

One engine, every surface

The app is one way in. The same librarian runs everywhere else:

| Surface | Use it for | Start here | |---|---|---| | Desktop app (Dazzi) | Browsing and asking in one window | NomaDamas/AutoRAG-app (Fair Source, FSL-1.1-MIT) | | Terminal UI | Interactive, steerable search sessions | autorag tui | | Messenger | Asking the librarian from a chat app | Telegram, Discord | | CLI | Scripts, indexing, health checks | CLI Command Reference | | MCP server | Feeding retrieval to Claude Code, Codex, and other agents | AutoRAG Lite MCP Server | | TypeScript API | Embedding the librarian in your own app | Programmatic usage | | Agent skills | Letting a coding agent install and drive AutoRAG | For AI Agents |


What is AutoRAG Agent?

Search tools dump file paths and matching lines — forcing you to open files, read context, and synthesize answers yourself.

AutoRAG Agent is a personal librarian agent that helps with your office work. Built on the Pi agent framework, a single configured model searches your files, mail, chats, and notes in place, opens source documents directly via bash to verify ground truth, and curates answers into clean, numbered knowledge units. Because it works for you rather than only on your index, it can also act on your files when you ask, such as organizing, renaming, moving, or editing them with a record of every change:

You ask:  "What changes were made to the cloud infrastructure contract in Q3?"

AutoRAG Agent:
[1] Enterprise Compute Discount — AWS annual discount tier increased to 28% based on commitment volume. (contracts/cloud-2026.pdf:p.4)
[2] Regional Data Residency — Explicit compliance clause pinning customer data storage to the Seoul AWS region. (/slack/legal-ops/chunks/318)
[3] SLA Guarantee — Guaranteed uptime threshold adjusted to 99.95% with penalty credits starting at 15 minutes downtime. (contracts/sla-addendum.md:lines 45-62)

Core Values

<p align="center"> <img src="assets/autorag-agent-principles.png" alt="AutoRAG Agent Core Principles" width="100%" /> </p>

Three principles drive every design decision in AutoRAG Agent:

  1. Never migrate your data to search it. Traditional RAG systems force you to upload, ETL, and duplicate your files into a centralized vector database. AutoRAG Agent federates your data in place, querying CLI-native stores (lazykatok, discrawl, slacrawl, mailcrawl) where your data already lives. Results retain opaque, source-native identities (/kakao/..., /slack/...) that preserve local access control and privacy. (See our Competitive Landscape Study on why in-place federation is the durable differentiator).

  2. Just works — no RAG degree required. No pipeline tuning, no vector-DB maintenance, and no remote embedding keys required. AutoRAG Agent automatically manages MinSync for incremental Change Data Capture (CDC) chunking and provides a local embedding backend out of the box with zero external telemetry. A remote rerank model is an opt-in extra: it runs only when you name one in rerank.model, and otherwise the first answer is built from each source's own top 10.

  3. Fast by design. Rather than coordinating slow multi-agent hierarchies, a single configured model owns the entire retrieval, direct-read, and curation loop. Local CDC chunks (SPLADE sparse, vector, and hybrid modes) deliver rapid, low-latency turnaround across multi-turn research queries.


Architecture & How It Works

AutoRAG Agent orchestrates five integrated subsystems:

  1. Retrieval Memory (check_memory): After each answer, cited evidence Jev judges to genuinely support it is stored in ~/.autorag/memory.json. Later searches receive this conversation's evidence, similar past questions, and long-term insights as advisory reference — it never reorders results or overrides current evidence. See docs/retrieval-memory.md.
  2. Pluggable Multi-Method Retrieval:
    • SPLADE Sparse Search: Learned-sparse keyword ranking via MinSync's KURE-Sparse-nano encoder over parsed markdown mirrors; it replaced BM25 in MinSync 0.6 and matches Korean inflected forms (인증서를 → 인증서) with no tokenizer library. Exact identifiers among many look-alike files rank less reliably than with BM25. See docs/minsync-setup.md.
    • Semantic Vector Search: Dense vector retrieval over CDC chunks via the shared MinSync embedder.
    • Hybrid Search: MinSync fuses sparse and vector ranking over the same chunks.
    • Jikji Find-First Discovery: Local CLI-backed fast discovery answer packs.
    • Everything File-Name Search (Windows): The bundled voidtools Everything indexes file and folder names under your search roots so the agent finds files by name, extension, path, size, or date instantly (everything_search).
    • FSearch File-Name Search (macOS/Linux): fsearch-cli (FSearch) keeps a live, per-workspace name index of your search roots so the agent finds files by name, extension, path,

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars5.9k
CategoryAI
Updated6h ago
Forks515

Languages

TypeScript

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions