Universal CDP compatibility
Kernel browsers work with any framework or tool that supports the Chrome DevTools Protocol (CDP). This means you can:- Use any agent framework: Integrate with popular frameworks like Browser Use, Stagehand, Playwright, Puppeteer, Selenium, and more
- Connect via CDP: All browsers expose a CDP WebSocket URL for direct connection
- No vendor lock-in: Switch between frameworks or use multiple frameworks simultaneously
- Standard protocols: Built on open standards that work with the entire browser automation ecosystem
Computer Use
For vision-language models (VLMs) that predict browser actions from screenshots, Kernel provides Computer Controls APIs that enable direct mouse, keyboard, and screen interactions. These low-level controls let you:- Capture screenshots to send to your VLM
- Execute predicted actions (clicks, typing, scrolling, dragging)
- Build custom agentic loops with any VLM provider
Popular Framework Integrations
Kernel provides detailed guides for popular agent frameworks:- Agent Browser - Browser automation CLI for AI agents
- Browser Use - AI browser agent framework
- Claude Agent SDK - Run Claude Agent SDK automations in cloud browsers
- Stagehand - AI browser automation with natural language
- Computer Use (Anthropic) - Claude’s computer use capability
- Computer Use (OpenAI) - OpenAI’s computer use capability
- Computer Use (Gemini) - Gemini’s computer use capability
- Computer Use (OpenAGI) - OpenAGI’s computer use capability
- Computer Use (Yutori) - Yutori n1 pixels-to-actions model
- Laminar - Observability and tracing for AI browser automations
- Magnitude - Vision-focused browser automation framework
- Notte - AI agent framework for browser automation
- Val Town - Serverless function runtime
- Vercel - Deploy browser automations to Vercel
- Web Bot Authentication - Create signed Chrome extensions for web bot authentication
- 1Password - Use credentials from your 1Password vaults for Managed Auth