Reor is a local AI note-taking app for people who want to search their own writing, find connections between ideas and ask questions about their notes. The project is archived and no longer maintained. It runs on macOS, Windows and Linux, and it's open source under AGPL-3.0.
Its main distinction is how it brings related material into the writing process. While you edit a note, a sidebar can show other notes with similar content. Those connections appear automatically, so you can revisit an idea without having linked the notes yourself. Semantic search also finds notes by meaning rather than relying only on matching words.
The question-and-answer feature retrieves relevant passages from your collection and gives them to an LLM as context for its response. This makes your own notes the material for the conversation. The editor supports Markdown, and Reor keeps notes in a local folder. Existing Markdown collections can serve as its library, though frontmatter may not parse correctly.
Reor uses Ollama for local LLMs, with Transformers.js and LanceDB supporting local embeddings and retrieval. You can download and run models from within the app. Notes and their search data stay on your machine when you use the local setup.
You can also connect to an OpenAI-compatible API, including Oobabooga or OpenAI. A local backend keeps model processing on your hardware; choosing a cloud service sends the question and retrieved note context to that service.
Claim this page and we'll verify you by hand. Reor gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Reor?Promote it
Something wrong or outdated on this page?
922Updated 5 months agoMIT
macOS · Windows · Linux · Docker · Web#llama.cpp backend#LM Studio integration#MLX
Eclaire is a self-hosted AI assistant for notes, documents, photos, bookmarks and tasks. You can ask questions about saved material, inspect the sources behind an answer and ask the assistant to create notes or update tasks. Scheduled automations handle recurring requests such as a weekly task summary.
14.2KUpdated 1 week agoAGPL-3.0
macOS · Windows · Linux · Docker · Web#Multilingual#Ollama integration#OpenAI-compatible API
16.3KUpdated 2 days ago
macOS · Windows · Linux#LM Studio integration#Ollama integration#OpenAI-compatible API
9.4KUpdated 1 day agoMIT
macOS · Windows · Linux · iOS · Android#LM Studio integration#MCP#Ollama integration
46Updated 5 days agoAGPL-3.0
macOS · Windows · Linux · Browser Extension#Code execution#GGUF#llama.cpp backend
77KUpdated 3 months agoAGPL-3.0
macOS · Windows · Linux · iOS · Android · Web#MCP#Multi-user access#RAG
QAnything is a self-hosted knowledge base for people and teams who want to ask questions about their own documents, including collections that mix Chinese and English. It can answer in either language regardless of the document's language, and runs locally through Docker on Windows, macOS and Linux.
SurfSense is an open-source NotebookLM alternative that turns documents into cited answers and editable deliverables on your computer. It's a desktop app for Windows, macOS and Linux, aimed at people working with confidential files, research or study material. You don't need an account.
Anarlog, formerly Hyprnote, is a desktop AI meeting notetaker for people who want to keep private conversations on their own hardware. It captures audio from your device without adding a bot to the call and stays hidden during screen sharing. The app runs on macOS, Windows and Linux; its community application is open source under the MIT license.
Vyact is an open source desktop workspace for people who want to use a local LLM with their documents, email and code. It runs on Apple Silicon Macs, Windows and Linux x64 under the AGPL-3.0 license. Intel Macs aren't supported.
AppFlowy is a self-hosted Notion alternative for teams that want project management, shared documents, and AI in an environment they control. Its self-hosted enterprise offering can run on premises, in your own cloud, or in an air-gapped environment. Self-hosted LLMs and embedding models let you keep AI processing and workspace data inside your infrastructure, with no vendor access to your instance.