librarian-index

Community

Make your libraries semantically searchable.

AuthorJoranHonig
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Converts scattered library files into a unified semantic index so researchers can retrieve conceptually relevant content even when exact keywords differ.

Core Features & Use Cases

  • Deterministic, idempotent indexing: content hashes produce stable IDs so re-indexing overwrites instead of duplicating.
  • Local embeddings and storage: chunks are embedded locally with FastEmbed and stored in a local Qdrant database for offline semantic search.
  • Flexible chunking and filters: splits markdown by headings and code by line windows, skips large files, and supports configurable extensions and collections.
  • Use Case: After adding a new git-backed library to libraries.yaml, run the indexer to make its documentation and code searchable by the librarian agent.

Quick Start

Run the librarian-index skill to build a semantic search index for all registered libraries.

Dependency Matrix

Required Modules

qdrant-client[fastembed]pyyamlfire

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: librarian-index
Download link: https://github.com/JoranHonig/grimoire/archive/main.zip#librarian-index

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.