A comprehensive browser automation and web interaction framework that empowers AI agents to navigate the web, extract structured data, and manage external integrations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install vibesurf
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install vibesurf using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is VibeSurf Browser Automation?
VibeSurf is a robust browser automation skill designed to act as the primary interface between AI agents and the live web. By providing a structured API to control real browsers, VibeSurf allows agents to perform everything from simple content fetching to complex, multi-step automated workflows. This tool is a cornerstone for developers building with Openclaw Skills who need their agents to interact with websites as a human would, but with the speed and precision of an automated system.
The skill is built on a delegation model, where a main entry point routes requests to specialized reference guides for tasks like financial data extraction, social media interaction, or precise DOM manipulation. Whether you are building a research assistant or an automated testing bot, VibeSurf provides the necessary infrastructure to handle the complexities of the modern web.
VibeSurf Browser Automation Use Cases
- Automated data extraction of prices, product lists, or tables from e-commerce and news sites.
- Executing complex web-based tasks like filling out multi-page forms or navigating authenticated portals.
- Performing real-time AI-powered web searches to supplement LLM knowledge with current information.
- Generating visual documentation through automated screenshots and page summaries.
- Integrating browser-based workflows with external tools like Gmail, GitHub, and Slack via Composio and MCP.
How VibeSurf Browser Automation Works
- Health Verification: The agent first checks the VibeSurf service status via the
/healthendpoint to ensure the automation engine is active. - Action Discovery: The agent queries the
/api/tool/searchendpoint to identify the most relevant action for the user's request. - Schema Validation: Before execution, the agent retrieves the specific JSON schema for the chosen action's parameters to prevent malformed requests.
- Task Execution: The agent sends a POST request to
/api/tool/executewith the validated parameters to trigger the browser action. - State Monitoring: For complex tasks, the agent continuously monitors the browser state using
get_browser_stateto decide on subsequent navigation or interaction steps.
VibeSurf Browser Automation Setup
To get started with VibeSurf within the Openclaw Skills ecosystem, ensure the service is running locally and the endpoint is accessible.
Set your environment variable:
export VIBESURF_ENDPOINT="http://127.0.0.1:9335"
Verify the connection:
curl $VIBESURF_ENDPOINT/health
Once verified, you can begin making API calls to search for actions or execute browser tasks directly through your agent.
VibeSurf Browser Automation Data Schema & Taxonomy
VibeSurf organizes its functionality through a series of structured API endpoints that handle discovery, configuration, and execution.
| Component | Endpoint | Description |
|---|---|---|
| Action Discovery | /api/tool/search |
Returns a list of available automation actions based on keywords. |
| Parameter Schema | /api/tool/{name}/params |
Provides the required JSON structure for a specific action. |
| Execution Engine | /api/tool/execute |
The primary POST endpoint for running browser commands. |
| Configuration | /api/config/* |
Manages LLM profiles, MCP server integrations, and scheduling. |
| File Management | /api/files/* |
Handles uploads and downloads generated during browser sessions. |
VibeSurf Browser Automation Advanced Features
- Autonomous Agents: Utilizes
browser-usefor goal-oriented, multi-step task completion without manual instruction for every click. - Hybrid Control Mode: Seamlessly fall back from high-level autonomous agents to precise, step-by-step browser manipulation when tasks become blocked.
- Extensible Integrations: Support for Model Context Protocol (MCP) and Composio allows the browser agent to interact with thousands of third-party apps.
- Automated Scheduling: Built-in support for cron-based workflows to perform recurring web scraping or monitoring tasks automatically.
- Custom JS Execution: Ability to inject and run custom JavaScript on any page for specialized data extraction or interaction patterns.
SKILL.md
Loading
Related Openclaw Skills
PokerPal Game Assistant
A specialized AI agent skill for querying and managing live poker game data, including player statistics and financial settlements.
OpenClaw Model Router Skill
A robust model routing solution for OpenClaw featuring prefix-based triggers, timezone-aware scheduling, and fail-safe production switching.
Free Search Aggregator
A robust, quota-aware search aggregator providing AI agents with reliable access to 12 web search providers with automatic failover.
Flash Redeem Knight
A browser automation skill that converts prepaid redemption links into ready-to-use pickup codes by automating store and option selection.
AIKEK API Crypto Research & Image Generation
A powerful suite of APIs for real-time cryptocurrency market analysis, on-chain research, and automated meme-style image generation.
Whisper Transcriber
A robust offline speech-to-text skill utilizing whisper.cpp for high-speed, local audio transcription across multiple formats.
METADATA
Featured*
