HomeProjectsArticlesPK BoardAbout
Explore Projects

Webwright

Active
GitHub Python MIT

Description

A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.

Key Features

  • Coding agent with terminal access that writes and executes Playwright scripts instead of predicting individual browser actions
  • Workspace-as-state architecture where code and logs persist, not browser sessions
  • Lightweight core at ~1.5k LoC with pluggable model backends (OpenAI, Anthropic, OpenRouter)
  • SOTA performance: 86.7% on Online-Mind2Web and 60.1% on Odysseys long-horizon tasks
  • Task2UI mode that renders task results into reusable HTML-based web applications
  • Seamless integration as a Claude Code skill, Codex plugin, or standalone CLI tool

Use Cases

💡 Complex web automation tasks requiring multi-step workflows like form filling and date selection
💡 Long-horizon research tasks spanning dozens of pages with iterative exploration
💡 RPA script development where browser sessions are disposable and code is reusable
💡 Web testing and QA across dynamic sites with lazy loading and re-rendering
💡 Converting natural language web tasks into executable Playwright scripts

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (6.0k stars)
  • • Permissive open-source license (MIT)
  • • Responsive to issues, low backlog

Tags

browser agent automation python web-agent

Categories

🌐 Browser Agent 🤖 Agent Framework

Quick Start

Install via pip (pip install webwright) and set up with playwright install. Run with: webwright --task "your task description" --backend openai. The agent writes Python scripts, executes them in browser sessions, inspects screenshots, and iterates until the task is complete.
Visit GitHub

Related Projects

ScaleCUA

1.1k · Python
Stale C

Open-sourced computer use agents that can operate on cross-platform environments including Windows, macOS, Ubuntu, and Android. ICLR 2026 Oral paper project.

browserpythonagent +1
  • · Cross-platform GUI operation: supports Windows, macOS, Ubuntu, Android, and Web environments
  • · Large-scale training data: operation trajectories across 6 operating systems and 3 task domains
  • · State-of-the-art performance: MMBench-GUI L1-Hard 94.4%, OSWorld-G 60.6%, WebArena-Lite-v2 47.4%
View on GitHub

PyWinAssistant

1.3k · Python
Stale C

The first open-source Artificial Narrow Intelligence generalist agent that fully operates GUIs using only natural language. Uses Visualization-of-Thought and Chain-of-Thought reasoning for spatial perception and HID simulation.

browseragentpython +2
  • · First open-source Computer-Using-Agent that operates GUIs through native Windows Accessibility APIs without OCR or pixel-level imaging
  • · Symbolic spatial mapping with hierarchical element tracking via OS-native parent/child relationships and coordinate systems
  • · Natural language to GUI automation: parse intent, map to UI elements, and generate adaptive workflows
View on GitHub