agent-browser-clawdbotHeadless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Install via ClawdBot CLI:
clawdbot install MaTriXy/agent-browser-clawdbotFast browser automation using accessibility tree snapshots with refs for deterministic element selection.
Use agent-browser when:
Use built-in browser tool when:
# 1. Navigate and snapshot
agent-browser open https://example.com
agent-browser snapshot -i --json
# 2. Parse refs from JSON, then interact
agent-browser click @e2
agent-browser fill @e3 "text"
# 3. Re-snapshot after page changes
agent-browser snapshot -i --jsonagent-browser open <url>
agent-browser back | forward | reload | closeagent-browser snapshot -i --json # Interactive elements, JSON output
agent-browser snapshot -i -c -d 5 --json # + compact, depth limit
agent-browser snapshot -s "#main" -i # Scope to selectoragent-browser click @e2
agent-browser fill @e3 "text"
agent-browser type @e3 "text"
agent-browser hover @e4
agent-browser check @e5 | uncheck @e5
agent-browser select @e6 "value"
agent-browser press "Enter"
agent-browser scroll down 500
agent-browser drag @e7 @e8agent-browser get text @e1 --json
agent-browser get html @e2 --json
agent-browser get value @e3 --json
agent-browser get attr @e4 "href" --json
agent-browser get title --json
agent-browser get url --json
agent-browser get count ".item" --jsonagent-browser is visible @e2 --json
agent-browser is enabled @e3 --json
agent-browser is checked @e4 --jsonagent-browser wait @e2 # Wait for element
agent-browser wait 1000 # Wait ms
agent-browser wait --text "Welcome" # Wait for text
agent-browser wait --url "**/dashboard" # Wait for URL
agent-browser wait --load networkidle # Wait for network
agent-browser wait --fn "window.ready === true"agent-browser --session admin open site.com
agent-browser --session user open site.com
agent-browser session list
# Or via env: AGENT_BROWSER_SESSION=admin agent-browser ...agent-browser state save auth.json # Save cookies/storage
agent-browser state load auth.json # Load (skip login)agent-browser screenshot page.png
agent-browser screenshot --full page.png
agent-browser pdf page.pdfagent-browser network route "**/ads/*" --abort # Block
agent-browser network route "**/api/*" --body '{"x":1}' # Mock
agent-browser network requests --filter api # Viewagent-browser cookies # Get all
agent-browser cookies set name value
agent-browser storage local key # Get localStorage
agent-browser storage local set key valagent-browser tab new https://example.com
agent-browser tab 2 # Switch to tab
agent-browser frame @e5 # Switch to iframe
agent-browser frame main # Back to main{
"success": true,
"data": {
"snapshot": "...",
"refs": {
"e1": {"role": "heading", "name": "Example Domain"},
"e2": {"role": "button", "name": "Submit"},
"e3": {"role": "textbox", "name": "Email"}
}
}
}-i flag - Focus on interactive elements--json - Easier to parseagent-browser wait --load networkidlestate save/load--headed for debugging - See what's happeningagent-browser open https://www.google.com
agent-browser snapshot -i --json
# AI identifies search box @e1
agent-browser fill @e1 "AI agents"
agent-browser press Enter
agent-browser wait --load networkidle
agent-browser snapshot -i --json
# AI identifies result refs
agent-browser get text @e3 --json
agent-browser get attr @e4 "href" --json# Admin session
agent-browser --session admin open app.com
agent-browser --session admin state load admin-auth.json
agent-browser --session admin snapshot -i --json
# User session (simultaneous)
agent-browser --session user open app.com
agent-browser --session user state load user-auth.json
agent-browser --session user snapshot -i --jsonnpm install -g agent-browser
agent-browser install # Download Chromium
agent-browser install --with-deps # Linux: + system depsSkill created by Yossi Elkrief (@MaTriXy)
agent-browser CLI by Vercel Labs
Generated Feb 23, 2026
This skill enables automated testing of complex single-page applications (SPAs) by using accessibility tree snapshots for deterministic element selection, ensuring reliable interaction with dynamic content. It is ideal for QA teams to perform regression testing, validate multi-step workflows, and maintain session isolation for parallel test execution. The ability to save and load state allows skipping repetitive login flows, improving efficiency.
Businesses can automate the monitoring of competitor prices and product details across e-commerce sites by navigating, interacting with search and filters, and extracting text or attributes from elements using refs. The skill handles complex SPAs and network control features like blocking ads or mocking APIs to streamline data collection. Session isolation allows simultaneous monitoring from different user perspectives or regions.
Financial institutions can automate compliance checks by browsing regulatory websites, filling forms, and extracting updated policy documents or data. The skill's deterministic element selection ensures accuracy in multi-step workflows, while state persistence and session management help maintain secure, isolated browsing contexts for sensitive data. Network control can block unnecessary resources to improve performance during audits.
Healthcare providers can automate data entry into patient portals or retrieve medical records by interacting with web forms and extracting information using ref-based commands. The skill's ability to wait for network idle and handle complex SPAs ensures reliable operation with slow-loading or dynamic healthcare systems. Session isolation allows managing multiple patient accounts securely without interference.
Marketing teams can automate tasks such as posting content on social media platforms, monitoring ad performance, and extracting analytics by interacting with web interfaces. The skill's performance optimization and session features enable managing multiple accounts or campaigns simultaneously. Screenshot and PDF capabilities allow visual documentation for reporting and analysis.
Offer a cloud-based service where users can schedule and run browser automation scripts for tasks like data extraction, testing, or monitoring, using this skill as the core engine. Revenue is generated through subscription tiers based on usage volume, number of sessions, or advanced features like network control and state persistence. This model targets businesses needing scalable, no-code or low-code automation solutions.
Provide consulting services to help enterprises integrate this skill into their existing workflows for specific use cases like compliance automation or e-commerce monitoring. Revenue comes from project-based fees for development, training, and ongoing support. This model leverages the skill's flexibility to address unique business needs, such as multi-session testing or complex SPA interactions.
Operate a managed service where clients outsource repetitive browser tasks, such as price monitoring or data entry, with guaranteed accuracy and performance using this skill. Revenue is generated through retainer agreements or pay-per-task models, focusing on industries like retail or healthcare. The skill's session isolation and state persistence ensure reliable, secure operations for multiple clients simultaneously.
💬 Integration Tip
Integrate this skill by using its JSON output for parsing refs in AI agents, and leverage session management to handle multiple browser contexts efficiently in automated workflows.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Manages project knowledge using ByteRover context tree. Provides two operations: query (retrieve knowledge) and curate (store knowledge). Invoke when user requests information lookup, pattern discovery, or knowledge persistence. Developed by ByteRover Inc. (https://byterover.dev/)