# stenolabs/stenoai

Steno is the highly secure privacy-first AI notepad & notetaker for all your confidential conversations. On Windows & MacOS.

Repository: https://github.com/stenolabs/stenoai
Canonical: https://ross.abutalabs.com/products/stenoai
Homepage: https://stenoai.co/
Language: Python
License: MIT
License Family: permissive
Topics: ai, localllm, meeting-notes, apple-silicon, meeting-minutes, sovereign-ai, windows, gemma4, government, privacy, defense, defense-tech, gov-tech
Last push: 2026-09-02T18:22:59+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 96, longevity 27
- inputs: {"age_days": 379, "days_push": 0, "days_rel": 30, "gap_med": 1.5, "n_releases_24m": 53}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1299, forks 178 (observed 2026-09-03T02:15:18.133732+00:00)

## What it is
Steno is a privacy-first desktop AI notepad and meeting notetaker that records, transcribes, summarizes, and lets you query meetings entirely on-device using local Whisper and Ollama models. It targets users with confidential conversations—government, defence, healthcare, legal, and executives—by ensuring no audio or data ever leaves the machine.

## Use cases
- transcribe meetings locally without cloud services
- summarize confidential meetings with a local LLM
- record both sides of a video call without a meeting bot
- ask questions about past meeting notes
- take notes in air-gapped or restricted environments
- generate meeting minutes for government or defence work
- mirror meeting notes into an Obsidian vault

## When to choose
- you handle confidential conversations where data cannot leave your premises
- you need offline transcription and summarization on macOS or Windows
- you want a bot-free notetaker that works with Zoom, Meet, or Teams via system audio
- you operate in government, defence, healthcare, or legal sectors with strict privacy requirements

## When to avoid
- you want cloud-based collaboration or shared team workspaces
- you need mobile or browser-based note taking
- your hardware cannot run local Whisper and LLM models comfortably
- you need multi-user editing or real-time shared notes

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, llm-inference, nlp, audio-processing, chatbot, rag
- domain: developer-tools, privacy, speech-processing, self-hosted, healthcare, legal
- platform: windows, python
- tags: meeting-notes, transcription, on-device-ai, whisper, ollama, sovereign-ai, notetaker, local-llm, obsidian-integration, natural-language-processing, macos, desktop

## Member repositories
- stenolabs/stenoai (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:18.133732+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:54:49.260534+00:00, confidence not recorded.
  - readme: https://github.com/stenolabs/stenoai (fetched 2026-09-03T02:15:18.133732+00:00, sha 5ddacc53f555)
  - homepage: https://stenoai.co/ (fetched 2026-08-29T12:11:22.041768+00:00, sha 068b096f3a15)
  - site_page: https://docs.stenoai.co (fetched 2026-08-29T12:11:22.051240+00:00, sha 401d5d92fd9b)
- Data as of 2026-08-30T08:39:29.467469+00:00.