微软发布终端原生 Web Agent 框架：Webwright https://github.com/microsoft/webwright…

核心设计：代码即动作 传统网页智能体采用“观察→预测下一步点击→执行“的循环，每一步都依赖 LLM 判断。Webwright 的做法更贴近软件工程师思维： · 让 LLM 写 Playwright 脚本 —— 把网页操作变成可运行的 Python 程序 · 工作区即状态 —— 脚本、截图、日志保存在本地，浏览器会话可随时重建 · 终端优先 —— 核心循环只有三个模块约 1000 行代码，无隐藏编排层

这种模式产生的“副产物“是可复用的自动化程序，而非一次性交互痕迹。

性能表现：SOTA 水平 · Online-Mind2Web (300 任务)：86.7% (GPT-5.4)，同类开源框架中最高 · Odysseys (200 长程任务，平均 76.1 步)：60.1% (GPT-5.4)，较此前 SOTA (+15.6pt)，较基线 GPT-5.4 (+26.6pt) · Claude Opus 4.7：84.7% / 难例 80.5%，难例上超越 GPT-5.4

架构极简 Runner (150行) -> Model Endpoint (550行) -> Environment (300行)

· 仅依赖 httpx、pydantic、playwright、typer · 无多智能体系统、无图引擎、无插件层 · 支持 OpenAI、Anthropic、OpenRouter 后端

产品化与集成 · Claude Code：插件 /plugin install webwright@webwright，支持 /webwright:run 和 /webwright:craft · OpenAI Codex：插件市场安装，通过 @ webwright 调用 · OpenClaw / Hermes：共享 skills/webwright/ 目录，统一技能规范

关键创新点 · Task2UI 模式 (2026-05-11 新增) —— 任务完成后自动渲染为 HTML 应用，结果可视化且可重用 · 脚本可复用性 —— 即使是 Qwen-3.5-9B 这样的小模型，在预置工具脚本辅助下也能达到 66.2% 的难例完成率 · 可审计性 —— 每次运行都保存轨迹、截图、报告，便于调试和回归

microsoft/webwright

Source: https://github.com/microsoft/webwright

Webwright

Turn Your Coding Models to Be State-of-the-art Browser Agents

• 📝 Blog: Webwright: A Terminal Is All You Need For Web Agents
• 🌐 Project Page: microsoft.github.io/Webwright

Webwright gives LLM a terminal where it can launch multiple browser sessions to inspect the page and complete a web task. It captures and inspects page screenshots/states only when needed. It enforces each web task to be completed end-to-end within a re-runnable Python script, i.e. your web agent browsing history is a single code file. No multi-agent system, no graph engine, no plugin layer, no hidden orchestration — just a terminal, a browser, and a model.

Already got your favorite agents, and wonder how to make Claude Code, Codex, Hermes, OpenClaw more capable in browser tasks? Consider adding Webwright plugin/skills!

📰 News

• 2026-05-11 — Support Task2UI mode: Webwright completes the task and renders task results into an HTML-based web app you can easily view and reuse.
• 2026-05-06 — Codex and Claude Code plugin manifests added; install via /plugin install webwright@webwright. OpenClaw and Hermes Agent integrations shipped; the same skills/webwright/ folder now loads across Claude Code, Codex, OpenClaw, and Hermes.
• 2026-05-04 — Initial public release: ~1.5k LoC, OpenAI / Anthropic / OpenRouter backends, Playwright environment.

🎥 Demo

https://github.com/user-attachments/assets/4ed94cd5-11be-4daa-b2d7-1260a803baca

📊 Performance

State-of-the-art on two real-website benchmarks with a 100-step budget — see the blog post for full details.

• 🏆 Online-Mind2Web (300 tasks): 86.7% with GPT-5.4 — highest among open-sourced harnesses in the AutoEval category. Claude Opus 4.7 reaches 84.7%, and is stronger on the hard split (80.5% vs. 76.6% for GPT-5.4 at N=100).
• 🚀 Odysseys (200 long-horizon tasks): 60.1% with GPT-5.4 (avg. 76.1 steps) — +15.6 points over the prior SOTA (Opus 4.6 at 44.5%, using vision based approach and persistent browser) and +26.6 points over base GPT-5.4 (33.5% using xy-coordinate prediction and persistent browser).
• 🧠 Code-as-action beats coordinate prediction: Webwright substantially outperforms a reproduced GPT-5.4 screenshot+xy-coordinate baseline across all difficulty splits.
• 🧰 Small models + reusable tools: generated scripts can be packaged as parameterized CLI tools — even Qwen-3.5-9B completes tasks well on Online-Mind2Web sites with 5+ tools available.

🗺️ Project Map

webwright/
├── pyproject.toml           # package: webwright
├── src/webwright/
│   ├── run/cli.py           # CLI entrypoint (`webwright`)
│   ├── agents/default.py    # core agent loop
│   ├── environments/        # Playwright browser workspace
│   ├── tools/               # image_qa, self_reflection
│   ├── models/              # openai_model, anthropic_model, base
│   ├── config/              # base.yaml, model_openai.yaml, model_claude.yaml
│   └── utils/
├── assets/
│   └── task_showcase/       # tiny Flask dashboard for repeatable runs
│       ├── app.py
│       ├── templates/       # dashboard.html, task.html
│       └── tasks/<short_id>/ # task.json + report.json per task
├── tests/
└── outputs/                 # run artifacts (trajectories, screenshots)

📰 Task Showcase (repeatable runs as a dashboard)

A tiny Flask app under assets/task_showcase/ consolidates Webwright runs for repeatable odyssey tasks (deals, inventory, listings, job boards, weather, etc.) into a single dashboard. Each task ships only two files — task.json (metadata) and report.json (curated, structured output: sources + result sections like tables, lists, summaries) — and the templates render them generically, so adding a new task is just dropping a new folder in assets/task_showcase/tasks/.

pip install flask
python assets/task_showcase/app.py    # http://127.0.0.1:5005

To have Webwright produce a renderer-ready task folder at runtime, stack the Task Showcase overlay:

python -m webwright.run.cli \
    -c base.yaml -c model_openai.yaml -c task_showcase.yaml \
    -t "<repeatable web task>" \
    --task-id my_repeatable_task \
    -o outputs/default

The run writes task_showcase/tasks/<short_id>/task.json and report.json inside the output workspace. Render those generated files without copying them back into the repo:

python assets/task_showcase/app.py \
    --tasks-dir outputs/default/<run>/task_showcase/tasks

🚀 Quick Start

Prerequisites

• Python 3.10+
• Chromium installed through Playwright
• An API key for your chosen backend (OpenAI, Anthropic, or OpenRouter)

Install

pip install -e .
playwright install chromium

Run

Export credentials for the configured backend (for example, OPENAI_API_KEY with model_openai.yaml or ANTHROPIC_API_KEY with model_claude.yaml). The image_qa and self_reflection tools use the same configured model by default, so an Anthropic run does not require an OpenAI key. Then:

python -m webwright.run.cli \
    -c base.yaml -c model_openai.yaml \
    -t "Search for flights from SEA to JFK on 2026-08-15 to 2026-08-20" \
    --start-url https://www.google.com/flights \
    --task-id demo_openai \
    -o outputs/default

🚩 Flags

🔌 Use as a Plugin

Webwright ships plugin manifests for both Claude Code (.claude-plugin/plugin.json) and OpenAI Codex (.codex-plugin/plugin.json), with the shared skill at skills/webwright/ and slash commands at skills/webwright/commands/. The host agent drives the Webwright loop natively — no extra LLM API key or cost beyond your host subscription. Hosts that read PNG screenshots natively skip the image_qa / self_reflection tools.

Common runtime deps (install once after either path):

pip install -e .
playwright install chromium

# 1. Add this repo as a Claude Code plugin marketplace
/plugin marketplace add microsoft/Webwright

# 2. Install the plugin from that marketplace
/plugin install webwright@webwright

/plugin marketplace add /absolute/path/to/Webwright
/plugin install webwright@webwright

/webwright:run search Google Flights for flights from SEA to JFK on 2026-08-15 to 2026-08-20
/webwright:craft search a ticket on Google Flights from LAX to SFO depart June 7 return June 14

# 1. Add this repo as a Codex plugin marketplace
codex plugin marketplace add microsoft/Webwright

# 2. Open the plugin browser and install Webwright
codex
/plugins

codex plugin marketplace add /absolute/path/to/Webwright

@webwright search Google Flights for flights from SEA to JFK on 2026-08-15 to 2026-08-20

openclaw plugins install /absolute/path/to/Webwright
openclaw gateway restart   # reload so the plugin and skill are picked up

openclaw plugins list | grep webwright
openclaw skills  list | grep webwright   # should show "✓ ready"

mkdir -p ~/.hermes/skills
ln -sfn /absolute/path/to/Webwright/skills/webwright ~/.hermes/skills/webwright

Credits

• SWE-agent/mini-swe-agent — design inspiration for the minimal agent loop.
• Playwright — browser automation.

Citation

If you use Webwright in your research or build on it, please cite this repository:

@misc{webwright2026,
  title        = {Webwright: A terminal is all you need for web agents},
  author       = {Lu, Yadong and Xu, Lingrui and Huang, Chao and Awadallah, Ahmed},
  year         = {2026},
  howpublished = {\url{https://github.com/microsoft/Webwright}},
  note         = {GitHub repository}
}

Omar Shahine (@OmarShahine): Need to try this. Hoping for massive boost over Playwright for browser automation.