agent-browser
agent-browser is a skill for automating browser-based workflows and web interactions through programmatic control. Built as part of an open-source AI agent framework, it enables you to orchestrate web tasks, integrate with large language models, and connect external tools into executable automation chains. Perfect for developers building intelligent agents that need to interact with web applications and handle complex browser operations at scale.
agent-browser is a skill for automating browser-based workflows and web interactions through programmatic control. Built as part of an open-source AI agent framework, agent-browser enables you to automate browser interactions and web tasks programmatically, orchestrate web tasks, integrate with large language models, and connect external tools into executable automation chains. It's perfect for developers building intelligent agents that need to interact with web applications and handle complex browser operations at scale.
AI-generated summary based on this skill's SKILL.md
Install
countbot-ai/CountBot/agent-browser · repository language: Python
git clone https://github.com/countbot-ai/CountBot
cp -r CountBot/workspace/skills/agent-browser ~/.claude/skills/agent-browserFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is agent-browser and what can it automate?
agent-browser is a skill for automating browser-based workflows and web interactions through programmatic control. Built as part of an open-source AI agent framework, agent-browser enables you to automate browser interactions and web tasks programmatically, orchestrate web tasks, integrate with large language models, and connect external tools into executable automation chains. It's perfect for developers building intelligent agents that need to interact with web applications and handle complex browser operations at scale.
Can agent-browser fill forms and click buttons programmatically?
Yes, agent-browser supports testing web applications and forms with automation, which includes the ability to fill forms and click buttons programmatically. This makes agent-browser ideal for automating repetitive web interactions, testing web application workflows, and building intelligent agents that can navigate and manipulate web page elements without manual intervention.
Does agent-browser support web scraping and data extraction?
agent-browser includes robust capabilities for extracting data and scraping content from websites. You can use agent-browser to programmatically extract data from web pages, making it suitable for building data collection pipelines, content aggregation tasks, and integration with AI agents that need to gather information from multiple web sources.
How does agent-browser handle login automation and session management?
agent-browser provides functionality for managing authentication and persistent browser sessions. This capability allows you to automate login workflows, maintain session state across multiple interactions, and handle complex authentication scenarios—essential for building agents that need to interact with protected web applications and maintain user context throughout automated workflows.
Can agent-browser run multiple browser automation tasks concurrently?
Yes, agent-browser supports running parallel browser automation tasks concurrently. This enables you to scale your automation workflows by executing multiple browser sessions simultaneously, making agent-browser efficient for high-volume web automation tasks, batch processing, and scenarios where you need to interact with multiple websites or perform parallel testing operations.
What license does agent-browser use?
agent-browser is released under the MIT license, which is a permissive open-source license. This means you can freely use, modify, and distribute agent-browser in both commercial and personal projects, subject to the terms of the MIT license.
SKILL.md
rendered from the published skill — quoted content, verbatim
Browser Automation with agent-browser
Core Workflow
Every browser automation follows this pattern:
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(get element refs like@e1,@e2) - Interact: Use refs to click, fill, select
- Re-snapshot: After navigation or DOM changes, get fresh refs
```bash agent-browser open https://example.com/form agent-browser snapshot -i
Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"
agent-browser fill @e1 "user@example.com" agent-browser fill @e2
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 11 files
workspace/skills/agent-browser/SKILL.md
workspace/skills/agent-browser/references/authentication.md
workspace/skills/agent-browser/references/commands.md
workspace/skills/agent-browser/references/proxy-support.md
workspace/skills/agent-browser/references/session-management.md
workspace/skills/agent-browser/references/snapshot-refs.md
workspace/skills/agent-browser/references/video-recording.md
workspace/skills/agent-browser/templates/authenticated-session.sh
workspace/skills/agent-browser/templates/capture-workflow.sh
workspace/skills/agent-browser/templates/form-automation.sh
workspace/skills/agent-browser/安装与配置手册.md