# ishan0102/vimGPT

Browse the web with GPT-4V and Vimium

Repository: https://github.com/ishan0102/vimGPT
Canonical: https://ross.abutalabs.com/products/vimgpt
Language: Python
License: MIT
License Family: permissive
Last push: 2024-09-25T21:47:45+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 73
- inputs: {"age_days": 1031, "days_push": 707, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2649, forks 199 (observed 2026-08-28T04:07:06.910701+00:00)

## What it is
vimGPT is a Python application that lets GPT-4V browse and interact with the web visually using Playwright and the Vimium keyboard-navigation Chrome extension. It gives multimodal LLMs a keyboard-based interface to click and navigate pages without needing DOM text, and includes an optional voice mode.

## Use cases
- browse the web with GPT-4V vision only
- let an AI agent click links and navigate pages without DOM access
- automate web tasks using a multimodal LLM
- control a browser with voice commands
- experiment with vision-based web agents
- prototype browser automation without DOM parsing

## When to choose
- you want to experiment with vision-only web browsing agents
- you need a lightweight research prototype for multimodal browser control
- you want to avoid feeding page DOM text to the model
- you want voice-driven browser automation

## When to avoid
- you need a production-grade, reliable web automation agent
- you require JSON mode or function calling support from the vision API
- you need to automate tasks on your own logged-in browser with credentials
- you need low-cost, high-volume automation since vision API calls are expensive

## Facets
- artifact type: application
- maturity: experimental
- function: agent-framework, browser-extension, llm-inference, workflow-automation
- domain: artificial-intelligence, browser-extensions
- platform: python, browser
- tags: gpt-4v, vimium, web-browsing-agent, playwright, multimodal, voice-control, ai-agents, automation, desktop

## Member repositories
- ishan0102/vimGPT (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:06.910701+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 2026-08-30T02:18:54.777978+00:00, confidence not recorded.
  - readme: https://github.com/ishan0102/vimGPT (fetched 2026-08-28T04:07:06.910701+00:00, sha 68e6fa96cf5b)
- Data as of 2026-08-30T08:39:29.467469+00:00.