[GitHub Trending] vercel-labs/agent-browser

7.6 relevance

Browser automation CLI for AI agents, directly matches AI agent orchestration and developer experience.

AI/ML github.com

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

For platform engineers building agent orchestration pipelines, this provides a deterministic, low-latency browser automation primitive that integrates cleanly with MCP and shell-based agent loops, avoiding the overhead of Playwright/Puppeteer for simple read-click cycles.

Key Takeaways

Evaluate agent-browser as a drop-in replacement for Playwright in agentic workflows where each step is a single shell call and you need explicit element-state validation.

Browser automation CLI for AI agents. Contribute to vercel-labs/agent-browser development by creating an account on GitHub.

Summary

Vercel Labs released agent-browser, a native Rust CLI that gives AI agents a browser they can drive one command at a time via compact accessibility-tree snapshots with element refs. It runs as a background daemon over Chrome DevTools Protocol, supports multiple engines (Chrome for Testing, Lightpanda, Obscura, Mobile Safari, cloud providers), and ships versioned skills for agent harnesses like MCP servers. The tool stays open between commands for low-latency multi-step automation, with explicit failure handling for hidden or covered elements.