// the find
karakeep-app/karakeep
A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search
Karakeep is a self-hosted bookmark manager that stores links, notes, images, and PDFs with LLM-based auto-tagging, full-text search via Meilisearch, and full-page archival. It targets developers and homelab users who want a Pocket/mymind replacement they actually own. The feature surface is broad: browser extensions for all three major browsers, iOS/Android apps, RSS hoarding, OCR, yt-dlp video archiving, and a rule engine.
The dependency stack is honest about what it is — Meilisearch for search rather than trying to roll their own, Drizzle for migrations, tRPC end-to-end. Full-page archival via monolith and video archiving via yt-dlp means you actually keep the content, not just the URL, which is the whole point of a hoarder app. The rule-based engine for automated organization is a real differentiator over simpler read-it-later apps. MCP server and CLI both exist, so agentic workflows (save, search, organize) are possible without screen-scraping the UI.
Meilisearch is a required external dependency — you can't run this with just Postgres and a web server, which raises the ops burden for something people want to just quietly run. The README lists 'semantic search across bookmarks' as planned, meaning the LLM tagging is classification, not embeddings-based retrieval; if you save 5000 links, keyword search may disappoint. Heavy development warning is still up and the rename from Hoarder to Karakeep was recent, which means config keys, Docker image names, and community resources are still in transition — expect confusion if you're following old tutorials. AGPL-3.0 is load-bearing: if you embed this in anything commercial or SaaS, you're obligated to open-source your entire stack.