{"enrichment":{"faq":[{"a":"Core is a high-performance command-line interface built in Rust that enables AI agents to control web browsers programmatically. Core automates website interactions by providing streamlined CLI commands for navigation, element clicking, form filling, and data extraction. Instead of raw HTML, core uses compact accessibility-tree references to read page content and take screenshots, making it ideal for AI agent workflows that need efficient, structured browser control.","q":"What is core and how does it automate website interactions?"},{"a":"Core provides CLI commands that let you interact with web page elements using accessibility-tree references rather than fragile selectors. To fill a form and click a button, you reference elements by their compact accessibility identifiers, then issue commands to populate form fields and trigger clicks. This approach keeps your automation robust across page layout changes and integrates seamlessly into agent scripts and MCP server environments.","q":"How do I fill a form and click a button with core?"},{"a":"Yes, core can take screenshots of webpages programmatically via its CLI. When you capture a screenshot with core, it also provides an accessibility-tree snapshot that maps interactive elements to compact references. This dual output\u2014visual snapshot plus structured element references\u2014lets AI agents both see the page and interact with it using reliable, machine-readable identifiers instead of parsing raw HTML.","q":"Can core take a screenshot of a webpage programmatically?"},{"a":"Core maintains browser session state across multiple CLI commands, allowing you to authenticate once and then perform subsequent interactions without re-logging in. This persistent session handling is essential for multi-step workflows where an AI agent needs to log in, navigate authenticated pages, and extract data across several command invocations. Core's session persistence simplifies complex automation scenarios that would otherwise require managing cookies and tokens manually.","q":"How does core handle authentication and persist browser session state across multiple commands?"},{"a":"Core's snapshot and refs approach captures both a visual screenshot and an accessibility-tree representation of the page, with each interactive element assigned a compact reference identifier. This tutorial-friendly pattern lets AI agents understand page structure without parsing HTML directly. References remain stable across commands, enabling reliable element targeting and reducing failures from stale selectors or dynamic content changes.","q":"What is the core agent-browser snapshot and refs tutorial approach?"},{"a":"Core can be installed globally or as a project dependency to add browser automation capabilities to your AI systems. For MCP server integration, core's CLI commands map naturally to structured tool definitions, allowing agents to call browser actions through standardized interfaces. This integration pattern works seamlessly in eve agent sandboxes and other structured tool environments, giving AI systems reliable, permission-bounded access to web automation without embedding a full browser library.","q":"How do I integrate core into an MCP server or AI agent sandbox?"}],"shadow_tags":["cli-automation","web-interaction","headless-chrome","accessibility-tree","form-filling","data-extraction","session-persistence","multi-tab-control","ai-agent-tools","browser-scripting"],"summary_rewrite":"Core provides a high-performance command-line interface built in Rust that enables AI agents to control web browsers programmatically. Automate navigation, element interaction, form submission, and data extraction with a streamlined CLI designed for agent workflows. Install globally or as a project dependency to add browser automation capabilities to your AI systems."},"files":[{"bytes":28015,"path":"skill-data/core/SKILL.md","sha256":"b8db03838026ea61c167828342fdb89276039d1ea15ac04c11dfb507a23c5b34","url":"https://skillfed.io/files/vercel-labs/agent-browser/core/06673863/SKILL.md"}],"id":"vercel-labs/agent-browser/core","links":{"html":"https://skillfed.io/vercel-labs/agent-browser/core","md":"https://skillfed.io/vercel-labs/agent-browser/core.md","repo":"https://github.com/vercel-labs/agent-browser"},"meta":{"agents_supported":[],"first_seen":"2026-07-28","forks":2572,"language":"Rust","last_updated":"2026-07-28","license":"Apache-2.0","name":"core","publisher":"vercel-labs","stars":39346},"relations":{"similar":[{"id":"fcakyon/claude-codex-settings/agent-browser"},{"id":"harnessclaw/harnessclaw-engine/agent-browser"},{"id":"julianromli/ai-skills/agent-browser"},{"id":"Factory-AI/factory-plugins/browser-navigation"},{"id":"Factory-AI/factory-plugins/agent-browser"},{"id":"wshaddix/dotnet-skills/agent-browser"},{"id":"UnicomAI/wanwu/agent-browser"},{"id":"UnicomAI/wanwu/agent-browser-clawdbot"},{"id":"vercel-labs/open-agents/agent-browser"},{"id":"code-yeongyu/oh-my-openagent/agent-browser"}]},"slug":{"owner":"vercel-labs","repo":"agent-browser","skill":"core"},"version":"06673863"}