HN Showcase
Back to browse
Platypus – Local meeting transcription, notes, and chat (Tauri, Rust)

Platypus – Local meeting transcription, notes, and chat (Tauri, Rust)

by pixelmash13·Apr 29, 2026·3 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidCozySolve My Problem

Process inspection auto-detection for Zoom and Teams is a genuinely clever local-first trick.

Strengths
  • •Detects active calls via CptHost and AudioService processes without needing API access.
  • •Tauri and Rust stack keeps the binary under 30MB with no Electron bloat.
  • •Local HNSW vector search ensures your knowledge base never leaves your machine.
Weaknesses
  • •Local Whisper performance relies heavily on Apple Silicon, limiting Windows utility.
  • •Requires manual LLM API configuration, adding friction compared to all-in-one SaaS.
Category
Productivity
Target Audience

Privacy-focused professionals and developers wanting local-first meeting notes

Similar To

Granola · NotebookLM · Otter.ai

Post Description

Hi HN — I built Platypus as I wanted to combine note taking, live transcription and knowledge base management in one app. Granola / Notebook LM free local alternative. It's a Tauri/Rust desktop app that does on-device meeting transcription via whisper.cpp, notes in TipTap, and per-project HNSW vector search across your knowledge base. You bring your own LLM (Claude, OpenAI, Gemini, or local Ollama).

A few things that were interesting to figure out:

Zoom/Teams meeting auto-detection works via process inspection — Zoom spawns CptHost only during an active call (not when the app is just open), and Teams's audio.mojom.AudioService sub-process. No Zoom/Teams API access needed. Local Whisper works great - on Mac. Old PC experience not recommended, so I built in API transcription switch if the local model is slow.

Repo: https://github.com/pixelsmasher13/platypus Site: https://platypusnotes.com

Feedback welcome!

Similar Projects