🔥
HotRepo
meetily — Self-host Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcr
📦
Zackriya-Solutions

meetily — Self-host Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcr

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.

12.5k🍴 1.3kRust📜 mit#ai#ai-meeting-assistant#llm#local-ai

meetily

**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. **

11,557 stars on GitHub · 🍴 1,132 forks · 📜 License: mit · 💻 Language: Rust

What is meetily?

A local-first AI meeting assistant makes a lot more sense when your calls include customer data, legal discussions, roadmap planning, or anything you would rather not ship to a SaaS vendor. Meetily’s differentiator is simple and strong: live transcription, diarization, and AI summaries can run fully on your own machine, with no cloud dependency.

Main components

  • Real-time meeting capture with live transcription for calls and recorded conversations.
  • Speaker diarization to separate who said what during the meeting.
  • Local AI transcription using Parakeet or Whisper, with a focus on faster-than-real-time performance.
  • AI-generated meeting summaries, action items, and notes through Ollama or other supported LLM providers.
  • Desktop app support for macOS and Windows, with Linux mentioned in the project documentation.
  • Flexible model/backend options, including local Ollama, Claude, Groq, OpenRouter, or OpenAI-compatible endpoints.

Clear use cases

  • Record internal engineering meetings and produce searchable notes without sending IP or roadmap details to a third-party note taker.
  • Give consultants, lawyers, healthcare teams, and finance staff a private transcription workflow for sensitive client conversations.
  • Run meeting notes on laptops in offline or restricted-network environments where cloud transcription is not allowed.
  • Build a self-hosted meeting intelligence setup for teams that want control over models, storage, and compliance boundaries.
  • Replace per-seat AI note-taking subscriptions with an open-source desktop tool backed by local models.

The biggest strength is data sovereignty — Meetily keeps the core meeting workflow local, from audio processing to transcription and summarization when paired with Ollama. That matters because most commercial AI meeting assistants are built around convenience at the cost of control: your meeting audio, transcript, speaker data, and generated notes typically pass through vendor infrastructure. Meetily is not just “another meeting bot”; it is a practical alternative for teams that need AI notes but cannot justify handing confidential conversations to a black-box SaaS platform.

There are trade-offs. Running transcription and LLM summarization locally means hardware matters, model setup can take some tuning, and accuracy will depend on your chosen models, microphones, accents, and meeting conditions. The existence of a Pro edition also means some business-friendly features, such as advanced exports, custom templates, auto-meeting detection, and built-in compliance workflows, may sit outside the community edition. Still, the open-source version covers the core value proposition well: capture the meeting, transcribe it live, identify speakers, and generate useful notes under your control.

Best for privacy-conscious developers, consultants, regulated teams, and IT managers who want AI meeting notes without routing sensitive conversations through a cloud meeting assistant.

Topics: the project is tagged with popular topics:

  • 🏷️ ai
  • 🏷️ ai-meeting-assistant
  • 🏷️ llm
  • 🏷️ local-ai
  • 🏷️ mac
  • 🏷️ meeting-minutes
  • 🏷️ meeting-notes
  • 🏷️ offline-first
  • 🏷️ ollama
  • 🏷️ parakeet

📸 Screenshots

meetily

Zackriya-Solutions%2Fmeeting-minutes | Trendshift

Meetily Demo

Meetily Demo

Import and Enhance

Quick install

See the README for detailed install instructions. Most projects support Docker — if the repo has a Dockerfile, use:

git clone https://github.com/Zackriya-Solutions/meetily.git
cd meetily
docker build -t meetily .
docker run -d -p 8080:8080 meetily

Minimum system requirements

Component Recommended
RAM 4096 MB
CPU 2 vCPU
Disk 50 GB SSD
OS Ubuntu 22.04 LTS / Debian 12
Docker 24.0+

⚡ Deploy fast on VSIS

Use the VSIS VPS Standard 4GB RAM / 2 vCPU / 50GB SSD (~150k/tháng) plan from VSIS.NET — high-speed VN-based VPS, 24/7 support, ideal for running meetily smoothly.

🎯 Benefits:

  • One-command docker compose up -d deploy in 2 minutes
  • Dedicated IPv4, root access, unmetered domestic bandwidth
  • Daily snapshot backup
  • Free install assistance from the VSIS team

👉 See matching VPS plans at vsis.net

Resources


Article compiled from GitHub data on 05/05/2026. Star/fork counts may have changed — see live numbers via the GitHub link.