# oxylabs/browser-agent-py

AI Browser Agent is an advanced Browser AI tool developed by Oxylabs AI Studio that automates real user browsing tasks using natural language instructions.

Repository: https://github.com/oxylabs/browser-agent-py
Canonical: https://ross.abutalabs.com/products/browser-agent-py
Homepage: https://aistudio.oxylabs.io/apps/browser_agent?utm_source=877&utm_medium=affiliate&utm_campaign=ai_studio&utm_content=browser-agent-py&groupid=877&transaction_id=102f49063ab94276ae8f116d224b67
License Family: other
Topics: ai-agent, ai-agents, ai-browser, ai-studio, browser-agent, browser-ai, browser-automation, browser-automation-studio
Last push: 2026-04-02T09:46:19+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 75, release rhythm 35, longevity 23
- inputs: {"age_days": 324, "days_push": 153, "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 1505, forks 2 (observed 2026-08-28T04:04:54.925034+00:00)

## What it is
A Python SDK for Oxylabs AI Studio's Browser Agent, a cloud service that automates real-user browsing tasks (clicking, typing, scrolling, screenshots) driven by natural language prompts or structured action lists. It extracts structured data from JavaScript-rendered pages in JSON, Markdown, HTML, or PNG formats without manual scraping rules.

## Use cases
- automate browser tasks with natural language
- scrape javascript-rendered websites without writing selectors
- extract structured json data from web pages
- fill forms and click through sites programmatically
- take screenshots of dynamic web pages
- replace selenium/puppeteer scripts with ai-driven browsing

## When to choose
- you want to describe browsing tasks in plain English instead of scripting selectors
- target sites are dynamic, JavaScript-heavy, or protected by anti-bot measures
- you need schema-based structured extraction with multiple output formats
- you prefer a managed cloud service over maintaining browser infrastructure

## When to avoid
- you need a free, self-hosted, or offline solution - it requires an Oxylabs API key and paid credits
- you need fine-grained, deterministic control over every browser action
- high-volume scraping where per-step credit costs would be prohibitive
- you need an OSI-approved open-source license - none is provided

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, web-scraping, browser-extension, llm-inference, data-generation
- domain: web-development, crawlers
- platform: python, cloud
- tags: browser-automation, ai-agent, natural-language-control, web-data-extraction, oxylabs, api-service, screenshots, schema-based-extraction, ai-agents, automation, data-engineering, web-server

## Member repositories
- oxylabs/browser-agent-py (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:54.925034+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 2026-08-30T04:32:42.899711+00:00, confidence not recorded.
  - readme: https://github.com/oxylabs/browser-agent-py (fetched 2026-08-28T04:04:54.925034+00:00, sha f09ae2011ac1)
  - homepage: https://aistudio.oxylabs.io/apps/browser_agent?utm_source=877&utm_medium=affiliate&utm_campaign=ai_studio&utm_content=browser-agent-py&groupid=877&transaction_id=102f49063ab94276ae8f116d224b67 (fetched 2026-08-29T11:37:32.903941+00:00, sha d42b3547f761)
  - site_page: https://aistudio.oxylabs.io/pricing (fetched 2026-08-29T11:37:32.912622+00:00, sha 9226846bdd8d)
  - site_page: https://aistudio.oxylabs.io/releases (fetched 2026-08-29T11:37:32.914718+00:00, sha 2807647bbec5)
- Data as of 2026-08-30T08:39:29.467469+00:00.