Enables AI assistants to control a web browser through Playwright-compatible tools, with an on-device decision engine for autonomous task completion and optional LLM escalation.
Enables coding agents to coordinate around shared project context, durable tasks, messages, artifacts, multimodal analysis requests, design-system checks, change proposals, and review requests through a compact MCP interface. It persists state locally in JSON and exposes tools, resources, and prompts for agent-to-agent workflows.