# MinorJerry/WebVoyager

Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"

Repository: https://github.com/MinorJerry/WebVoyager
Canonical: https://ross.abutalabs.com/products/webvoyager
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-03-04T03:36:39+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 68
- inputs: {"age_days": 952, "days_push": 912, "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 1122, forks 122 (observed 2026-08-28T04:03:40.033304+00:00)

## What it is
WebVoyager is the official code and dataset for a research paper on an end-to-end web agent powered by large multimodal models that completes user instructions by interacting with real websites via Selenium. It includes 643 annotated web task queries across 15 websites plus GAIA-derived tasks and a GPT-4V-based automated evaluation protocol.

## Use cases
- build a multimodal web browsing agent
- benchmark web agents on real website tasks
- evaluate web agents automatically with GPT-4V
- get a dataset of web navigation task queries
- research LLM-driven browser automation

## When to choose
- you need a research-grade benchmark for web agents
- you want to reproduce or extend the WebVoyager paper
- you need annotated real-website task queries with reference answers

## When to avoid
- you need a production-ready browser automation tool
- you want a maintained agent framework rather than research code
- you need offline or sandboxed web environments

## Facets
- artifact type: dataset
- maturity: active
- function: agent-framework, machine-learning, web-scraping, benchmarking, data-generation
- domain: artificial-intelligence, large-language-models
- platform: python, windows, cross-platform
- tags: web-agent, multimodal, lmm, selenium, gpt-4v, research-code, web-navigation, benchmark-dataset, ai-agents, natural-language-processing, datasets, linux, macos

## Member repositories
- MinorJerry/WebVoyager (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:40.033304+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 2026-08-30T06:40:54.679299+00:00, confidence not recorded.
  - readme: https://github.com/MinorJerry/WebVoyager (fetched 2026-08-28T04:03:40.033304+00:00, sha c7cfe10edaeb)
- Data as of 2026-08-30T08:39:29.467469+00:00.