# elfvingralf/macOSpilot-ai-assistant

Voice + Vision powered AI assistant that answers questions about any application, in context and in audio.

Repository: https://github.com/elfvingralf/macOSpilot-ai-assistant
Canonical: https://ross.abutalabs.com/products/macospilot-ai-assistant
Language: JavaScript
License Family: other
Last push: 2023-12-21T19:48:09+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 71
- inputs: {"age_days": 1002, "days_push": 986, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1157, forks 48 (observed 2026-08-28T04:03:48.341982+00:00)

## What it is
macOSpilot is a macOS desktop AI assistant built with Electron that answers spoken or typed questions about whatever application is currently active. It screenshots the active window, transcribes your voice via OpenAI Whisper, queries GPT Vision with the screenshot, and replies as text overlay plus audio via OpenAI TTS.

## Use cases
- ask questions about any app on screen without switching windows
- get voice answers about what's displayed in the current application
- trigger an AI assistant with a global keyboard shortcut
- get in-context help for unfamiliar software UIs
- hands-free AI assistant while working on macOS
- screenshot-based question answering with GPT Vision

## When to choose
- you're on macOS and want a context-aware assistant for any active application
- you prefer speaking questions and hearing audio answers
- you want a self-hosted Electron app wired to your own OpenAI API key

## When to avoid
- you need Windows or Linux support - it's macOS only
- you don't want to pay for OpenAI API usage or send screenshots to the cloud
- you need a polished, packaged product - it requires manual setup and has no license

## Facets
- artifact type: application
- maturity: experimental
- function: speech-recognition, tts, llm-inference, ocr, chatbot
- domain: artificial-intelligence, developer-tools, desktop-applications, large-language-models
- platform: -
- tags: voice-assistant, screen-context, openai, gpt-vision, keyboard-shortcut, audio-answers, macos, electron, nodejs, desktop

## Member repositories
- elfvingralf/macOSpilot-ai-assistant (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:48.341982+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 2026-08-30T06:32:02.305643+00:00, confidence not recorded.
  - readme: https://github.com/elfvingralf/macOSpilot-ai-assistant (fetched 2026-08-28T04:03:48.341982+00:00, sha 297f45e2ba9a)
- Data as of 2026-08-30T08:39:29.467469+00:00.