claude-obsidian

Claude Obsidian turns your Obsidian vault into an autonomous knowledge engine powered by Claude Code. Instead of passive AI chat, it actively reads sources you drop in, extracts entities and concepts, creates cross-referenced wiki pages, and maintains a session context cache so the next conversation picks up where you left off. Ten skill commands cover everything from ingestion to vault linting to autonomous web research.

Setup is a git clone and a shell script. The vault structure works directly in Obsidian with no plugin conflicts. It supports six wiki modes (Website, GitHub, Business, Personal, Research, Book/Course) and runs an 8-category vault linter that catches orphan notes, dead links, stale claims, and missing cross-references. Batch ingestion runs through parallel agents.

Solo knowledge workers who already use Obsidian and Claude Code get a structured workflow for turning raw sources into an organized, interlinked wiki. The hot.md context cache is a clever solution to Claude Code's session boundary problem.

The catch: you need a Claude Code subscription to run any of it, so it's free software that requires paid infrastructure. Heavy ingestion sessions burn through Claude Code context fast. The quality depends on prompt engineering that could break with model updates.