gitmyhub

meetily

Rust ★ 13k updated 16d ago

Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetily (Meetly Ai - https://meetily.ai) is the #1 Self-hosted, Open-source Ai meeting note taker for macOS & Windows.

Meetily records, transcribes, and summarizes your meetings entirely on your own computer, no audio or text ever leaves your machine, making it safe for sensitive or regulated conversations.

RustWhisperParakeetOllamaElectronsetup: easycomplexity 2/5

Meetily is a meeting assistant application that records, transcribes, and summarizes your meetings entirely on your own computer, without sending any audio or text to outside servers. It is designed for people who work with sensitive conversations and do not want their meeting content stored on third-party cloud infrastructure.

The transcription is done using open-source speech recognition models called Whisper and Parakeet, which run locally on your machine. As a meeting happens, Meetily produces a live transcript in real time. It also identifies different speakers in the recording, a feature called speaker diarization. After the meeting, it generates a written summary using a local AI model through a tool called Ollama. If you prefer, you can also point it at external AI services like Claude, Groq, or any OpenAI-compatible endpoint, but local processing is the default recommendation.

The application runs on macOS, Windows, and Linux. On macOS and Windows, prebuilt installers are available for download. Linux users build from source using the provided instructions. The backend is written in Rust for performance, and the frontend uses a standard web-based interface packaged as a desktop app.

The community edition is free and open source under the MIT license. A paid PRO version adds features like custom summary templates, PDF and Word document exports, automatic meeting detection, and built-in GDPR compliance tools, but the core product described in the README remains free.

The README positions the tool primarily for enterprises, legal teams, healthcare providers, and anyone in a regulated industry where cloud meeting tools create compliance or confidentiality risks. You can also import existing audio files to have them transcribed after the fact, or re-process recordings with a different AI model.

Where it fits