Reor - An open-source AI-powered personal knowledge management tool that automatically connects relevant notes.

What is Reor?

Reor is an open-source, localized AI-powered personal knowledge management application. It supports automatic linking of related notes, semantic search, and Q&A functionality. Users can edit notes using a Markdown editor similar to Obsidian. Reor utilizes technologies such as Ollama, Transformers.js, and LanceDB to enable local execution of LLM and embedded models, ensuring data privacy. Reor provides a local writing assistant to help users efficiently organize and retrieve knowledge. Reor supports multiple platforms, including Mac, Linux, and Windows, and users can easily download and install it.

Reor's main functions

• Automatically connect related notesReor can automatically identify and connect notes with similar topics or content without requiring users to manually create links.
• Semantic searchIt supports semantic search, so users don't need to remember the exact wording in their notes. They can simply enter relevant keywords and Reor will return the most relevant search results.
• Q&A FunctionIt has a built-in large language model (LLM) that allows users to ask questions, and the LLM provides answers based on all of the user's notes.
• Local priorityAll of Reor's functions run and are stored locally, ensuring data privacy.
• WYSIWYG Markdown EditorIt supports Markdown editing, allowing users to format notes using Markdown syntax. The editor provides a WYSIWYG experience.
• Local writing assistantIt provides a local writing assistant, allowing users to get suggestions and tips on relevant notes at any time while writing, helping them to write more fluently.
• Support local model executionIntegration with Ollam allows users to download and run local models directly in Reor, or connect to OpenAI-compatible APIs.
• Multi-platform supportIt supports multiple operating systems such as Mac, Linux, and Windows, allowing users to use Reor on different devices.

Reor's technical principles

• Vector DatabaseEach note is segmented and embedded into an internal vector database. Related notes are automatically connected based on vector similarity calculations.
• LLM Driver Q&AThis approach uses LLM (Large Language Model) for question answering and Retrieval Enhancement Generation (RAG) technology to retrieve relevant information from a notes corpus to assist in generating answers.
• Local model runningReor supports running LLMs and embedded models locally, based on technologies such as Llama.cpp, Transformers.js, and LanceDB, ensuring data privacy and performance optimization.
• Markdown parsing and editingReor uses Markdown as its note format and supports WYSIWYG editing, making it easy for users to quickly write and organize notes.
• Semantic search technologyBased on the embedding model, text is converted into vectors, and semantic search is performed using vector similarity to improve the accuracy and efficiency of the search.

Reor's official website address

• Project official website:https://www.reorproject.org/
• GitHub repository:https://github.com/reorproject/reor

Application scenarios of Reor

• Personal knowledge managementIt helps users organize their notes, quickly find relevant content based on automatic links and semantic search, and improves knowledge retrieval efficiency.
• academic researchIt facilitates researchers in organizing literature notes and experimental records, quickly connecting related research content, assisting in paper writing, integrating and citing existing results, and improving research efficiency.
• TeamworkIt helps team members share knowledge, organize project documents, quickly find relevant experience and best practices within the team, improve collaboration efficiency, and support real-time document collaboration.
• Enterprise knowledge managementIt manages internal enterprise documents and policy files, builds project knowledge bases to facilitate employee access and learning, improves overall efficiency, and supports the management of employee training materials.
• Creative WritingCreative professionals can manage their inspiration logs and drafts, quickly connect them to spark more ideas, and assist in the creation of novels, scripts, etc., by organizing character backgrounds and plot clues.