Your Personal Librarian Agent. Ask anything on your computer, organize files, remember important info and files.
AutoRAG Agent is a librarian-style system that searches files on a computer, checks the original documents, and organizes findings into numbered knowledge units using multiple retrieval methods. It helps an agent answer questions from local documents without first copying them into a centralized vector database, while the repository also maintains the earlier AutoRAG tool for optimizing retrieval-augmented-generation pipelines. The catalogue entries provide skills and instructions for working with AutoRAG Agent.
Latest release v2.13.0 — AutoRAG v2.13.0 · 25 Oct 2026
3 files for GitHub Copilot, Codex, OpenCode and Claude Code: AutoRAG copilot-instructions.md, AutoRAG AGENTS.md, Datasource skill integration — 16,952 tokens loaded in every session.
.github/copilot-instructions.md D 3,237 tok AGENTS.md C 13,715 tok .github/ISSUE_TEMPLATE/datasource-skill.md A 12 tok These files are Marker-Inc-Korea/AutoRAG's own configuration — they tell GitHub Copilot, Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.