Reor
Open-source private AI note-taking app for researchers - local LLM runs entirely on your device, semantic note search, and automatic linking of related ideas.
Reor is a free, open-source AI research notebook that runs all AI features locally on your machine using Ollama models, with no data sent to external servers. It enables semantic search across your entire note vault, automatic suggestion of connections between related notes, and direct chat with your knowledge base - all without a cloud subscription. Notes are stored as plain markdown files, ensuring full data ownership and compatibility with tools like Obsidian. It is aimed at researchers, academics, and security-conscious professionals who need AI-assisted knowledge management without sharing private data with third-party LLM providers.
Key Features
- Fully local AI - runs on Ollama models entirely on your device with no external API calls or data sharing
- Semantic note search - finds related notes across your entire vault by meaning rather than exact keyword match
- Automatic note linking - AI suggests connections between related ideas as you write and build your knowledge base
- Chat with notes - ask questions across your entire note library and get answers grounded in your own content
- Plain markdown storage - notes saved as standard .md files, compatible with Obsidian, Logseq, and other tools
- Cross-platform desktop app - available for macOS, Windows, and Linux via open-source GitHub releases
Use Cases
- Researchers managing large personal knowledge bases who need AI assistance without sharing private data externally
- Academics building second-brain systems with AI-powered connection finding across hundreds of notes
- Security and compliance-conscious users who cannot use cloud AI tools due to data sensitivity requirements
- Developers wanting a local alternative to Notion AI or NotebookLM that works fully offline
Pros
- Fully local - no data leaves your device, suitable for confidential research and sensitive note-taking
- Free and open source - no subscription fees and community-driven development on GitHub
- Markdown files mean you own your data and can migrate to any other tool without lock-in
Cons
- Requires local LLM setup via Ollama - not a turnkey experience for users unfamiliar with local model setup
- AI quality depends on local hardware - weaker machines produce noticeably slower and less capable results
- Fewer integrations and less polished UX compared to commercial alternatives like NotebookLM or Mem
Reor Alternatives
Explore similar tools and alternatives
Looking for alternatives to Reor? Here are some similar tools you might like:
Google NotebookLM
Google's AI research tool that answers questions from your uploaded documents and generates audio overviews.
Khoj
Open-source personal AI assistant that searches and chats over your notes, documents, and web history - 20,000+ GitHub stars, free to self-host.
Logseq
Open-source local-first knowledge management with outliner-based notes, bidirectional links, and AI writing assistance - 400,000+ active users.
Ready to try Reor?
Visit the official website to explore all features and get started with Reor today.
Reviews
0 reviews for Reor
Based on 0 reviews
Share your experience
Log in to write a review for Reor
Perplexity AI
AI-powered answer engine that provides cited, up-to-date answers from the web with source transparency.
Google NotebookLM
Google's AI research tool that answers questions from your uploaded documents and generates audio overviews.
Hugging Face
The largest open-source AI model hub with 500K+ models, Spaces demos, and Inference Endpoints for developers.
Have an AI Tool?
List your AI tool for free, or go featured for top placement in your category - and reach thousands of potential users.
Submit Your Tool