Smart Connections (Obsidian)
Local semantic search across all your Obsidian notes. Embed-once, query-fast, fully offline.
Editorial verdict: “Best local semantic search for personal notes. Foundational layer for Obsidian RAG.”
Compatibility at a glance
Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"
What it is
For solo note-takers running Ollama on a laptop, Smart Connections turns Obsidian into a local semantic search engine. It embeds each note into a vector index using models like bge-small-en or nomic-embed-text, then surfaces related passages from any line you click. The entire pipeline runs offline on macOS, Linux, Windows, iOS, or Android with at least 4 GB VRAM. Initial embedding of a large vault takes time, and some advanced features require a paid license, but the core search is fast and reliable for vaults of 1,000+ notes. It also pairs with Obsidian Copilot for fully local RAG workflows.
✓ Strengths
- +Genuinely fast local semantic search
- +Embedding model + vector store all local
- +Great with vaults of 1000+ notes
△ Caveats
- −Initial embed of large vaults is slow
- −Some power features behind freemium gate
About the Editor plugin category
Plugin for VS Code, JetBrains, Vim, etc.
Where to go from here
Pre-filled with this app's recommended use case + budget tier. Get the full rig + runtime + model picks.
The full directory — filter by category, runtime, OS, privacy posture, or VRAM.
What this app talks to: Ollama, vLLM, llama.cpp, MLX, LM Studio. The upstream layer.
Did this app work for you on a specific rig? Submit the benchmark — it powers the model + hardware pages.