
Note Companion is an AI plugin for Obsidian that turns unprocessed notes and recordings into organized vault content. It's for researchers, students and people who collect meeting notes faster than they can sort them. The plugin runs in desktop Obsidian on Windows, macOS and Linux; it doesn't support Obsidian on mobile.
Organization covers folder placement, tags, filenames and formatting based on note content and your existing vault structure. You can review suggestions or let an Inbox folder handle them automatically. Templates structure notes and extract action items, while note splitting breaks long documents into smaller notes.
Chat uses your notes as context, with file, folder and tag mentions to select relevant material. It can summarize or edit text, rename files and split notes. For recorded material, the plugin transcribes audio and video files, turns YouTube videos into searchable notes with summaries, and creates meeting notes with discussion points, action items and embedded audio.
The code is open source under MIT. You can run a self-hosted backend, including through Docker, or use the Note Companion Cloud service, which requires an account. The plugin runs inside Obsidian, but the cloud service processes files remotely for AI features. Self-hosting puts the backend and provider keys on your server; it can connect to OpenAI, Claude, Gemini, Groq or a custom API endpoint. An experimental local Ollama path supports chat only, through a self-hosted backend or the plugin's local-model integration. Using an external AI provider still sends content to that provider.
Claim this page with an email at notecompanion.ai. Note Companion 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 Note Companion?Promote it
Something wrong or outdated on this page?
9.4KUpdated 1 day agoMIT
macOS · Windows · Linux · iOS · Android#LM Studio integration#MCP#Ollama integration
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.
4KUpdated 14 hours agoAGPL-3.0
Docker · Web#Multi-user access#Multilingual#Prompt caching
6Updated 2 weeks agoAGPL-3.0
macOS · Windows · Docker · Web#Hybrid search#LM Studio integration#MCP
Diariz is a self-hosted meeting transcription app for individuals and teams that want recordings and transcripts on their own server. It runs in Docker, with a browser interface and desktop apps for Windows and macOS (beta) for microphone and system audio capture. You can also upload existing recordings. Its source is available under AGPLv3.
2.6KUpdated 18 hours ago
macOS · Windows · Linux · Browser Extension#Ollama integration#ONNX#Persistent memory
212Updated 1 month agoMIT
macOS · Windows · Linux · Docker · Web#Multilingual#Ollama integration#Works offline
292Updated 1 week ago
macOS · Windows · Docker · Web#Human approval#Knowledge graphs#MCP
Revornix is a self-hosted AI workspace for people who collect research, articles and meeting recordings and want to search or ask questions across them. It turns saved material into Markdown, connects it in a personal knowledge graph, and produces summaries, illustrated reports or two-voice podcasts.
Speakr is a self-hosted transcription and note-taking app for meetings, interviews and lectures. Its browser interface can record microphone and system or browser-tab audio, or accept existing files. The app runs on your server and supports Docker deployment.
Natively is a desktop AI meeting assistant and interview copilot that combines live answers with on-device transcription. It runs on macOS, Windows and Linux, and suits people who want help during calls, searchable meeting records, or lecture summaries. It's source-available, with free personal and non-commercial use and paid offerings.
OpenScribe is a free, MIT-licensed AI medical scribe for clinicians who want control over where patient encounters are processed. It records visits, transcribes speech, and produces structured draft notes. Its fully local desktop workflow builds on StenoAI and uses Whisper for transcription and Ollama for note generation.