11 entries — sorted by GitHub stars.
Control a real browser from OpenClaw agents to interact with any website that requires JavaScript.
Let OpenClaw agents evaluate their own outputs and iteratively improve responses through self-critique loops.
Enable OpenClaw to run proactively in the background — monitoring conditions and initiating actions without user prompts.
Give OpenClaw direct control over the desktop GUI — clicks, typing, and screen reading on any application.
Expose Playwright browser automation capabilities to OpenClaw through the Model Context Protocol.
Let OpenClaw agents autonomously navigate websites, click links, and extract structured data.
Send an autonomous web rover from OpenClaw to crawl target sites and return structured content.
Run Playwright browser automation scripts from natural language instructions inside OpenClaw.
Run ComfyUI workflows in batch mode from OpenClaw — process multiple prompts in sequence without manual intervention.
Core headless browser engine for OpenClaw agents — the foundation for all browser-based automation skills.
Enable iterative self-reflection and output improvement loops within OpenClaw agent sessions.