agent-browser
agent-browser enables you to script and automate browser-based workflows directly from the command line. Execute web interactions, navigate pages, and handle complex tasks without manual intervention. Built for developers who need reliable programmatic control over web automation.
agent-browser is a command-line tool that enables you to script and automate browser-based workflows directly from the CLI. It provides programmatic control over web interactions, allowing you to navigate pages, execute complex tasks, and handle automation without manual intervention. The tool is built for developers who need reliable, scriptable access to browser automation capabilities.
AI-generated summary based on this skill's SKILL.md
Install
Intelligent-Internet/ii-agent/agent-browser · repository language: Python
git clone https://github.com/Intelligent-Internet/ii-agent
cp -r ii-agent/src/ii_agent/agents/skills/builtin/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 how does it automate browser interactions?
agent-browser is a command-line tool that enables you to script and automate browser-based workflows directly from the CLI. It provides programmatic control over web interactions, allowing you to navigate pages, execute complex tasks, and handle automation without manual intervention. The tool is built for developers who need reliable, scriptable access to browser automation capabilities.
Can agent-browser automate website interactions and fill forms programmatically?
Yes, agent-browser supports automating form filling, login, and authentication workflows. You can programmatically fill fields and click buttons to complete complex web interactions. This makes agent-browser ideal for automating repetitive tasks like account access, data entry, and multi-step web processes through CLI commands.
How does agent-browser help with web scraping and data extraction?
agent-browser enables you to extract data and take screenshots from web pages as part of your automation workflows. You can capture page content, retrieve specific data elements, and generate snapshots of web pages—all controlled programmatically through command-line commands. This functionality supports both content extraction and visual verification of web pages.
Is agent-browser suitable for testing web applications automatically?
Yes, agent-browser is designed to test web applications and verify page state changes. You can automate test scenarios, validate application behavior, and confirm that page elements respond correctly to interactions. This makes agent-browser a practical choice for web app testing automation and quality assurance workflows.
Does agent-browser support managing multiple parallel browser sessions?
agent-browser supports managing multiple parallel browser sessions for concurrent automation. This capability allows you to run simultaneous workflows across different browser instances, enabling efficient handling of large-scale automation tasks and concurrent web interactions from the command line.
What license does agent-browser use?
agent-browser is released under the Apache-2.0 license, which permits both commercial and non-commercial use with appropriate attribution and compliance with the license terms.
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
src/ii_agent/agents/skills/builtin/agent-browser/SKILL.md
src/ii_agent/agents/skills/builtin/agent-browser/references/authentication.md
src/ii_agent/agents/skills/builtin/agent-browser/references/commands.md
src/ii_agent/agents/skills/builtin/agent-browser/references/profiling.md
src/ii_agent/agents/skills/builtin/agent-browser/references/proxy-support.md
src/ii_agent/agents/skills/builtin/agent-browser/references/session-management.md
src/ii_agent/agents/skills/builtin/agent-browser/references/snapshot-refs.md
src/ii_agent/agents/skills/builtin/agent-browser/references/video-recording.md
src/ii_agent/agents/skills/builtin/agent-browser/templates/authenticated-session.sh
src/ii_agent/agents/skills/builtin/agent-browser/templates/capture-workflow.sh
src/ii_agent/agents/skills/builtin/agent-browser/templates/form-automation.sh