{"id":"856814ac-7b06-43e5-a68d-6f744fb7e2fd","entityType":"agent","slug":"quentintou-openclaw-skill-browser-use","name":"Browser Use","canonicalUrl":"https://xpersona.co/agent/quentintou-openclaw-skill-browser-use","canonicalPath":"/agent/quentintou-openclaw-skill-browser-use","generatedAt":"2026-04-17T04:05:55.475Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"description":"Autonomous browser automation for AI agents. Two tools: agent-browser (CLI Playwright for step-by-step control) and browser-use (Python autonomous agent that decides what to do on pages). Navigate, click, fill forms, scrape data, manage sessions, and run complex multi-step browser tasks. --- name: Browser Use description: > Autonomous browser automation for AI agents. Two tools: agent-browser (CLI Playwright for step-by-step control) and browser-use (Python autonomous agent that decides what to do on pages). Navigate, click, fill forms, scrape data, manage sessions, and run complex multi-step browser tasks. read_when: - Automating web interactions beyond simple fetch - Filling forms or completing mul","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 4 GitHub stars reported by the source. Last updated 4/15/2026.","installCommand":"git clone https://github.com/quentintou/openclaw-skill-browser-use.git","sourceUrl":"https://github.com/quentintou/openclaw-skill-browser-use","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/quentintou/openclaw-skill-browser-use","kind":"source"}],"safetyScore":94,"overallRank":32.7,"popularityScore":17,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Autonomous browser automation for AI agents. Two tools: agent-browser (CLI Playwright for step-by-step control) and browser-use (Python autonomous agent that de"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"swap","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":2,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"swap","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:swap|supported|profile"}},"adoption":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"stars":4,"forks":1,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":"4 GitHub stars"},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-04-14T22:24:36.959Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T05:21:22.124Z","lastCrawledAt":"2026-04-14T22:24:36.959Z","lastIndexedAt":null,"nextCrawlAt":"2026-04-15T22:24:36.959Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"git clone https://github.com/quentintou/openclaw-skill-browser-use.git","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://xpersona.co/api/v1/agents/quentintou-openclaw-skill-browser-use/snapshot","contractUrl":"https://xpersona.co/api/v1/agents/quentintou-openclaw-skill-browser-use/contract","trustUrl":"https://xpersona.co/api/v1/agents/quentintou-openclaw-skill-browser-use/trust"},"curlExamples":["curl -s \"https://xpersona.co/api/v1/agents/quentintou-openclaw-skill-browser-use/snapshot\"","curl -s \"https://xpersona.co/api/v1/agents/quentintou-openclaw-skill-browser-use/contract\"","curl -s \"https://xpersona.co/api/v1/agents/quentintou-openclaw-skill-browser-use/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_OPENCLEW","generatedAt":"2026-04-17T04:05:55.475Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://xpersona.co/api/v1/agents/quentintou-openclaw-skill-browser-use/dossier","snapshotUrl":"https://xpersona.co/api/v1/agents/quentintou-openclaw-skill-browser-use/snapshot","contractUrl":"https://xpersona.co/api/v1/agents/quentintou-openclaw-skill-browser-use/contract","trustUrl":"https://xpersona.co/api/v1/agents/quentintou-openclaw-skill-browser-use/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"readme":"---\nname: Browser Use\ndescription: >\n  Autonomous browser automation for AI agents. Two tools: agent-browser (CLI Playwright for step-by-step control)\n  and browser-use (Python autonomous agent that decides what to do on pages). Navigate, click, fill forms,\n  scrape data, manage sessions, and run complex multi-step browser tasks.\nread_when:\n  - Automating web interactions beyond simple fetch\n  - Filling forms or completing multi-step web flows\n  - Scraping structured data from dynamic pages\n  - Running an autonomous browsing agent for complex tasks\n  - Testing or interacting with authenticated web apps\n  - Taking screenshots or recording browser sessions\nmetadata:\n  clawdbot:\n    emoji: \"🌐\"\n    requires:\n      bins: [\"node\", \"npm\", \"python3\"]\n      system: [\"chromium\", \"xvfb\"]\nallowed-tools: Bash(agent-browser:*,browser-use-agent:*,xvfb-run:*)\n---\n\n# Browser Use — Autonomous Browser Automation\n\nTwo complementary tools for browser automation:\n\n| Tool | Best for | How it works |\n|------|----------|-------------|\n| **agent-browser** | Step-by-step control, scraping, form filling | CLI commands, you drive each action |\n| **browser-use** | Complex autonomous tasks | Python agent that decides actions itself |\n\n## Quick Start\n\n### agent-browser (recommended for most tasks)\n\n```bash\n# Navigate and inspect\nagent-browser open \"https://example.com\"\nagent-browser snapshot -i          # Get interactive elements with @refs\n\n# Interact using refs\nagent-browser click @e3            # Click element\nagent-browser fill @e2 \"text\"      # Fill input (clears first)\nagent-browser press Enter          # Press key\n\n# Extract data\nagent-browser get text @e1         # Get element text\nagent-browser get attr @e1 href    # Get attribute\nagent-browser screenshot /tmp/p.png # Screenshot\n\n# Done\nagent-browser close\n```\n\n### browser-use (autonomous agent)\n\n```bash\n# Run a full autonomous browsing task\nbrowser-use-agent \"Find the pricing for Notion and compare plans\"\n```\n\nThe agent will navigate, click, read pages, and return a structured result.\n\n## agent-browser — Full Reference\n\n### Navigation\n```bash\nagent-browser open <url>           # Navigate to URL\nagent-browser back                 # Go back\nagent-browser forward              # Go forward\nagent-browser reload               # Reload page\nagent-browser close                # Close browser\n```\n\n### Snapshot (page analysis)\n```bash\nagent-browser snapshot             # Full accessibility tree\nagent-browser snapshot -i          # Interactive elements only (recommended)\nagent-browser snapshot -c          # Compact output\nagent-browser snapshot -d 3        # Limit depth to 3\nagent-browser snapshot -s \"#main\"  # Scope to CSS selector\nagent-browser snapshot -i --json   # JSON output for parsing\n```\n\n### Interactions (use @refs from snapshot)\n```bash\nagent-browser click @e1            # Click\nagent-browser dblclick @e1         # Double-click\nagent-browser fill @e2 \"text\"      # Clear and type (use this for inputs)\nagent-browser type @e2 \"text\"      # Type without clearing\nagent-browser press Enter          # Press key\nagent-browser press Control+a      # Key combination\nagent-browser hover @e1            # Hover\nagent-browser check @e1            # Check checkbox\nagent-browser uncheck @e1          # Uncheck checkbox\nagent-browser select @e1 \"value\"   # Select dropdown option\nagent-browser scroll down 500      # Scroll page\nagent-browser scrollintoview @e1   # Scroll element into view\nagent-browser drag @e1 @e2         # Drag and drop\nagent-browser upload @e1 file.pdf  # Upload files\n```\n\n### Extract Data\n```bash\nagent-browser get text @e1         # Get element text\nagent-browser get html @e1         # Get innerHTML\nagent-browser get value @e1        # Get input value\nagent-browser get attr @e1 href    # Get attribute\nagent-browser get title            # Page title\nagent-browser get url              # Current URL\nagent-browser get count \".item\"    # Count matching elements\n```\n\n### Wait\n```bash\nagent-browser wait @e1             # Wait for element\nagent-browser wait 2000            # Wait milliseconds\nagent-browser wait --text \"Done\"   # Wait for text to appear\nagent-browser wait --url \"/dash\"   # Wait for URL pattern\nagent-browser wait --load networkidle  # Wait for network idle\n```\n\n### Screenshots, PDF & Recording\n```bash\nagent-browser screenshot path.png      # Save screenshot\nagent-browser screenshot --full        # Full page screenshot\nagent-browser pdf output.pdf           # Save as PDF\nagent-browser record start ./demo.webm # Start recording\nagent-browser record stop              # Stop and save\n```\n\n### Sessions (parallel browsers)\n```bash\nagent-browser --session s1 open \"https://site1.com\"\nagent-browser --session s2 open \"https://site2.com\"\nagent-browser session list\n```\n\n### State (persist auth/cookies)\n```bash\nagent-browser state save auth.json     # Save session (cookies, storage)\nagent-browser state load auth.json     # Restore session\n```\n\n### Cookies & Storage\n```bash\nagent-browser cookies                  # Get all cookies\nagent-browser cookies set name value   # Set cookie\nagent-browser cookies clear            # Clear cookies\nagent-browser storage local            # Get all localStorage\nagent-browser storage local set k v    # Set value\n```\n\n### Tabs & Frames\n```bash\nagent-browser tab                      # List tabs\nagent-browser tab new [url]            # New tab\nagent-browser tab 2                    # Switch to tab\nagent-browser frame \"#iframe\"          # Switch to iframe\nagent-browser frame main               # Back to main frame\n```\n\n### Browser Settings\n```bash\nagent-browser set viewport 1920 1080\nagent-browser set device \"iPhone 14\"\nagent-browser set geo 37.7749 -122.4194\nagent-browser set offline on\nagent-browser set media dark\n```\n\n### JavaScript\n```bash\nagent-browser eval \"document.title\"    # Run JS in page context\n```\n\n## browser-use — Autonomous Agent\n\nFor complex tasks where you want the agent to figure out the browsing steps:\n\n```bash\nbrowser-use-agent \"Your task description here\"\n```\n\n### Custom Script (advanced)\n\n```python\n# Run via: /opt/browser-use/bin/python3 script.py\nimport asyncio, os\nfrom browser_use import Agent, Browser\nfrom langchain_anthropic import ChatAnthropic\n\nasync def run():\n    browser = Browser()\n    llm = ChatAnthropic(\n        model='claude-sonnet-4-20250514',\n        api_key=os.environ['ANTHROPIC_API_KEY']\n    )\n    agent = Agent(\n        task=\"Compare pricing on 3 competitor sites\",\n        llm=llm,\n        browser=browser,\n    )\n    result = await agent.run(max_steps=15)\n    await browser.close()\n    return result\n\nasyncio.run(run())\n```\n\nYou can swap the LLM for any langchain-compatible model (OpenAI, Anthropic, etc).\n\n## Standard Workflow\n\n```bash\n# 1. Open page\nagent-browser open \"https://example.com\"\n\n# 2. Snapshot to see what's on the page\nagent-browser snapshot -i\n\n# 3. Interact with elements using @refs from snapshot\nagent-browser fill @e1 \"search query\"\nagent-browser click @e2\n\n# 4. Wait for new page to load\nagent-browser wait --load networkidle\n\n# 5. Re-snapshot (refs change after navigation!)\nagent-browser snapshot -i\n\n# 6. Extract what you need\nagent-browser get text @e5\n\n# 7. Close when done\nagent-browser close\n```\n\n## Important Rules\n\n1. **Always `snapshot -i` after navigation** — refs change on every page load\n2. **Use `fill` not `type`** for inputs — fill clears existing text first\n3. **Wait after clicks that trigger navigation** — `wait --load networkidle`\n4. **Close the browser when done** — `agent-browser close`\n5. **Google/Bing block headless browsers** (CAPTCHA) — use DuckDuckGo or `web_search` instead\n6. **Save auth state** for sites requiring login — `state save/load`\n7. **Use `--json`** when you need machine-parseable output\n8. **Use sessions** for parallel browsing — `--session <name>`\n\n## Troubleshooting\n\n- **Element not found**: Re-run `snapshot -i` to get current refs\n- **Page not loaded**: Add `wait --load networkidle` after navigation\n- **CAPTCHA on search engines**: Use DuckDuckGo or the `web_search` tool instead\n- **Auth expired**: Re-login and `state save` again\n- **Display errors**: The install script sets up Xvfb for headless rendering\n","readmeExcerpt":"--- name: Browser Use description: > Autonomous browser automation for AI agents. Two tools: agent-browser (CLI Playwright for step-by-step control) and browser-use (Python autonomous agent that decides what to do on pages). Navigate, click, fill forms, scrape data, manage sessions, and run complex multi-step browser tasks. read_when: - Automating web interactions beyond simple fetch - Filling forms or completing mul","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# Navigate and inspect\nagent-browser open \"https://example.com\"\nagent-browser snapshot -i          # Get interactive elements with @refs\n\n# Interact using refs\nagent-browser click @e3            # Click element\nagent-browser fill @e2 \"text\"      # Fill input (clears first)\nagent-browser press Enter          # Press key\n\n# Extract data\nagent-browser get text @e1         # Get element text\nagent-browser get attr @e1 href    # Get attribute\nagent-browser screenshot /tmp/p.png # Screenshot\n\n# Done\nagent-browser close"},{"language":"bash","snippet":"# Run a full autonomous browsing task\nbrowser-use-agent \"Find the pricing for Notion and compare plans\""},{"language":"bash","snippet":"agent-browser open <url>           # Navigate to URL\nagent-browser back                 # Go back\nagent-browser forward              # Go forward\nagent-browser reload               # Reload page\nagent-browser close                # Close browser"},{"language":"bash","snippet":"agent-browser snapshot             # Full accessibility tree\nagent-browser snapshot -i          # Interactive elements only (recommended)\nagent-browser snapshot -c          # Compact output\nagent-browser snapshot -d 3        # Limit depth to 3\nagent-browser snapshot -s \"#main\"  # Scope to CSS selector\nagent-browser snapshot -i --json   # JSON output for parsing"},{"language":"bash","snippet":"agent-browser click @e1            # Click\nagent-browser dblclick @e1         # Double-click\nagent-browser fill @e2 \"text\"      # Clear and type (use this for inputs)\nagent-browser type @e2 \"text\"      # Type without clearing\nagent-browser press Enter          # Press key\nagent-browser press Control+a      # Key combination\nagent-browser hover @e1            # Hover\nagent-browser check @e1            # Check checkbox\nagent-browser uncheck @e1          # Uncheck checkbox\nagent-browser select @e1 \"value\"   # Select dropdown option\nagent-browser scroll down 500      # Scroll page\nagent-browser scrollintoview @e1   # Scroll element into view\nagent-browser drag @e1 @e2         # Drag and drop\nagent-browser upload @e1 file.pdf  # Upload files"},{"language":"bash","snippet":"agent-browser get text @e1         # Get element text\nagent-browser get html @e1         # Get innerHTML\nagent-browser get value @e1        # Get input value\nagent-browser get attr @e1 href    # Get attribute\nagent-browser get title            # Page title\nagent-browser get url              # Current URL\nagent-browser get count \".item\"    # Count matching elements"}],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"Autonomous browser automation for AI agents. Two tools: agent-browser (CLI Playwright for step-by-step control) and browser-use (Python autonomous agent that decides what to do on pages). Navigate, click, fill forms, scrape data, manage sessions, and run complex multi-step browser tasks. --- name: Browser Use description: > Autonomous browser automation for AI agents. Two tools: agent-browser (CLI Playwright for step-by-step control) and browser-use (Python autonomous agent that decides what to do on pages). Navigate, click, fill forms, scrape data, manage sessions, and run complex multi-step browser tasks. read_when: - Automating web interactions beyond simple fetch - Filling forms or completing mul","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":406,"uniquenessScore":60,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-04-17T04:05:55.475Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_openclew","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}