Skip to main content

Browser Automation Pack

TrustedSandbox optionalv1.0.0MITPartially Verified42

by AgentNode · published 6 months ago · toolpack

Automate web browsing, form filling, and data extraction.

Headless browser automation using Playwright. Navigate pages, fill forms, click buttons, take screenshots, and extract structured data from dynamic websites.

langchaincrewaigeneric

Quick Start

bash
agentnode install browser-automation-pack

Runs in a subprocess with filtered environment by default. Declared permissions are policy-checked, not sandboxed.

Usage

From package
python
from browser_automation_pack.tool import run

result = run(
    capability="browser_automate",
    params={
        "url": "https://books.toscrape.com/catalogue/category/books/science_22/index.html",
        "actions": [
            {"type": "wait_for", "selector": ".product_pod"},
            {
                "type": "extract",
                "selector": ".product_pod",
                "fields": {
                    "title": "h3 a@title",
                    "price": ".price_color",
                    "availability": ".availability"
                }
            }
        ]
    }
)

for book in result["extracted_data"]:
    print(f"{book['title']} — {book['price']} ({book['availability'].strip()})")

Runs locally on your machine. No execution data is sent to AgentNode. Permissions are checked before execution. Learn how this works

Verification

low confidence42/100○ Partially Verified
smokeSandbox limitation: missing_system_dependency
+12/25
testsTests failed
0/15
importAll tools imported successfully
+15/15
installInstalled in 2.8s
+15/15
contractContract not validated
0/10
determinismNo determinism data
0/5
reliabilityNo stability data
0/10

Package installs and imports correctly. requires system dependencies not in sandbox.

install2.8s
import462ms
smoke1.2s
tests1.1s

This package requires system dependencies (e.g., Chromium, ffmpeg) not available in the sandbox.

Verified in limited mode (sandbox limitations active)

Python 3.12.3ffmpegpopplertesseractuv

Last verified 19d ago· Runner v2.0.0

Use this when you need to...

  • Scrape product prices from e-commerce sites
  • Fill and submit web forms automatically
  • Take screenshots of web pages for monitoring
  • Extract structured data from dynamic JavaScript pages
  • Automate login flows and authenticated scraping

README

Version History

Capabilities

browser_automationbrowser_automatetool

Permissions

Sandbox optionalFrom a trusted publisher — runs on the host by default. You can require isolation with sandbox.host_trust_policy.

Declared by the publisher. Checked before execution by the policy gate.

Networkunrestricted
Filesystemtemp
Code Executionlimited_subprocess
Data Accessinput_only
User Approvalonce

Permissions are policy-checked before execution. For trusted and curated packages that run on the host, network and filesystem access are policy-checked but not OS-sandboxed. When runtime isolation is required for untrusted/community code, AgentNode uses sandbox-or-fail-closed if the required container runtime and pinned image are available. Learn more

Privacy

All tool execution happens locally on your machine. AgentNode never receives:

  • • Tool inputs or outputs
  • • Execution logs
  • • Data your agent processes

Only install events and search queries are sent to the registry.

bash
agentnode install browser-automation-pack

Files (3)

License

MIT

Stats

Downloads0
Installs0
Versionv1.0.0
Published3/16/2026
Channelstable
Typetoolpack
Entrypointbrowser_automation_pack.tool

Compatibility

Frameworks

langchaincrewaigeneric

Runtime

python

Python Version

>=3.10

Trust & Security

PublisherTrusted
SignatureNone
ProvenanceNone
Security Issues0

Publisher

A

AgentNode

@agentnode