openbrowser: an autonomous web browsing framework for TypeScript that executes natural language tasks via Playwright

What it solves

Open Browser provides a way for AI agents to interact with the web autonomously. Instead of writing manual scripts for every website, users can describe a task in natural language, and the agent handles the navigation, clicking, typing, and data extraction required to complete it.

How it works

The framework uses a loop where an AI agent sends the current page state and the user's goal to a Large Language Model (LLM). The LLM determines the necessary actions—such as clicking a button or typing into a field—which are then executed via a Playwright browser instance. The agent continues this cycle of observation and action until the task is finished.

Who it’s for

It is designed for TypeScript developers who want to integrate autonomous web browsing capabilities into their applications or use a CLI to automate web tasks without manual coding.

Highlights

• Multi-model support: Compatible with OpenAI, Anthropic, and Google models via the Vercel AI SDK.
• Interactive REPL: Includes a live browser prompt for real-time debugging and prototyping.
• Sandboxed execution: Offers resource limits (CPU/memory) and domain restrictions for safer agent runs.
• Production-ready features: Includes stall detection, cost tracking, session management, and replay recording.