microsoft/Webwright

Health v2 · maintenance only

Flags: no_releases young

Adoption not part of the score

5947 stars · 380 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Webwright is a Python framework from Microsoft that turns coding LLMs into state-of-the-art browser agents by giving them a terminal to launch and control Playwright browser sessions. Each web task is completed end-to-end as a single re-runnable Python script, with optional skill reuse and integrations for Claude Code, Codex, and other agent harnesses.

Use cases

• automate long-horizon web tasks with an llm browser agent
• turn coding models like claude code into browser agents
• run web tasks end-to-end as re-runnable python scripts
• reuse solved web tasks as standalone code skills without tokens
• benchmark web agents on webarena-style tasks
• control multiple browser sessions from a terminal with playwright

When to choose

• you want a minimal, script-based browser agent without multi-agent orchestration
• you need state-of-the-art results on long-horizon web tasks
• you want to extend existing coding agents with browser capabilities
• you prefer reusable, verified code skills over repeated model calls

When to avoid

• you need a no-code visual browser automation tool
• you only need simple scraping without an LLM
• you require a mature GUI or managed cloud service

Facets

framework · maturity active

agent-framework web-scraping llm-inference workflow-automation browser-extension large-language-models web-development python cross-platform cli browser-agent playwright web-automation swe-agent claude-code-plugin skill-factory ai-agents automation

Member repositories

For agents

markdown · JSON · MCP: product_card(name="microsoft/Webwright")