Reor
AI note-taking app that builds connections between your notes automatically. Local, open-source.
Editorial verdict: “Best AI-first note app that's actually local. Niche but well-executed.”
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
Reor is for Ollama users who want their note-taking app to actively connect ideas rather than just store them. It runs a local LLM and embedder side-by-side, so as you write, it surfaces semantically related notes without any data leaving your machine. The auto-linking works best with a model like Llama 3.1 8B Q4_K_M plus nomic-embed-text, and it bridges to any OpenAI-compatible runtime. The trade-off is that the quality of those connections depends heavily on the local model you choose, and the app itself is less polished than Obsidian. It’s a solid choice if you value privacy over polish and don’t mind tweaking your model stack.
✓ Strengths
- +Local-first by design
- +Auto-link related notes feels magical when it works
- +Open-source AGPL
△ Caveats
- −Younger / less polished than Obsidian
- −Auto-linking quality depends on the local model
About the Productivity category
Note-taking, knowledge management, or workflow apps with AI.
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.