agent-browser

Solid

Specialized browser automation for agent workflows with structured data extraction, multi-step workflows, error recovery, and state persistence.

AI & Automation 3 stars 1 forks Updated yesterday Apache-2.0

Install

View on GitHub

Quality Score: 79/100

Stars 20%
20
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Agent Browser Skill ## Overview Specialized browser automation designed specifically for agent workflows. Unlike general browser use, this skill optimizes for: - Structured data extraction - Multi-step workflows - Error recovery - State persistence across sessions - Integration with agent memory systems ## Key Differentiator: Browser Use vs. Agent Browser | Feature | Browser Use | Agent Browser | |---------|-------------|---------------| | **Primary use** | One-off tasks | Recurring workflows | | **State** | Ephemeral | Persistent across sessions | | **Error handling** | Basic retry | Sophisticated recovery | | **Data extraction** | Raw scraping | Structured to QMD | | **Integration** | Manual | Automatic agent memory | ## Core Capabilities ### 1. Persistent Sessions ```javascript // Save browser state (cookies, localStorage) await agentBrowser.saveSession('instagram-auth', { cookies: await page.cookies(), localStorage: await page.evaluate(() => localStorage), timestamp: Date.now() }); // Resume later await agentBrowser.loadSession('instagram-auth'); ``` ### 2. Structured Data Pipeline ```javascript // Extract → Transform → Load to QMD const workflow = { source: 'https://apps.apple.com/charts', extract: async (page) => { return await page.evaluate(() => { return Array.from(document.querySelectorAll('.app')).map(app => ({ name: app.querySelector('.name').textContent, rank: app.querySelector('.rank').textContent, category: a...

Details

Author
Silex-Research
Repository
Silex-Research/DontPanic
Created
4 months ago
Last Updated
yesterday
Language
Python
License
Apache-2.0

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

1 Updated 4 days ago
NafisRayan
AI & Automation Listed

agent-browser

Headless browser automation using agent-browser CLI. This skill should be used when performing headless/background web scraping, parallel multi-site operations, or simple page queries that don't require login. Triggers on requests like "크롤링", "스크래핑", "페이지 정보", "헤드리스", "병렬로 웹 작업", "여러 사이트 동시에".

1 Updated 2 days ago
SONGYEONGSIN
AI & Automation Solid

agent-browser

Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms — for verification tasks, not unattended automation.

9 Updated 1 weeks ago
getpaperclipai