How do I install webwright?

Run these in Claude Code: /plugin marketplace add microsoft/Webwright then /plugin install webwright@webwright. Then prompt normally.

Does webwright auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Automation

Plugin

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

FLOW.md

microsoft@microsoft

GitHub

Plugin Signal75/100Solid

maintained97

capable29

documented100

adopted80

Install on Claude Code

> /plugin marketplace add microsoft/Webwright
> /plugin install webwright@webwright

Stats

Python HTML Bash Vercel Git

+4 tags

GitHub Playwright Anthropic OpenAI

5,899

Stars

372

Forks

Active

Maintenance

Python

Language

MIT

License

6d ago

Last commit

4mo ago

Created

Repo: microsoft/Webwright

In this plugin

2 commands 1 skill

commands
- craft
- run
skills
- webwright

See everything inside

What's inside

Webwright

📝 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

2026-07-21 — Skill Factory: every solve leaves a script behind, distilled into reusable, verified, parameterized code skills that rerun standalone with no model (~40 s, zero tokens). On WebArena, reuse lifts held-out accuracy 55% → 70% (+15 pp). See Skill Factory.
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.

Most web agents today treat the browser session itself as the workspace: at each step the model receives the current page state and predicts a single next operation — a click, a type, a DOM selector, or a short tool call. Whatever the format, the agent is locked into predicting one web action at a time inside a predefined interaction loop. That harness was useful when LLMs were weaker. As models get stronger at writing and debugging code, the same harness becomes a bottleneck.

Webwright takes a different stance: separate the agent from the browser, and treat the browser as something the agent can launch, inspect, and discard while developing a program. The persistent artifact is not the browser session — it's the code and logs in the local workspace.

🧱 Robust, reusable interaction with web environments — instead of fragile pixel-level actions, a coding agent with a terminal queries elements, waits for conditions, and handles dynamic behaviors like lazy loading or re-rendering. The resulting scripts can be rerun, adapted, and shared across tasks rather than rediscovered from scratch.
⚡ Efficient composition of complex workflows — multi-step interactions like selecting a date or filling a form become a compact program. Loops, functions, and abstractions let the agent generalize across similar tasks (e.g. different dates) without re-predicting the same low-level sequences. Fewer interaction rounds, faster execution, less error accumulation on long horizons.
🧪 Workspace-as-state, not browser-as-state — the agent can write exploratory scripts, spawn fresh browser sessions, and decide for itself when to capture screenshots and inspect failures, much like a human engineer iterating on an RPA script.
🪄 Surprisingly effective despite being minimal — this stripped-down setup turns out to handle complex and especially long-horizon web tasks well (see Performance).

Most web agent frameworks bury the actual agent loop under layers of abstractions. Webwright takes the opposite stance:

🪶 Lightweight by design — core agent loop in a single ~450-line file, Playwright environment in ~570 lines, CLI in ~150 lines.
🧩 Pluggable model backends — OpenAI, Anthropic, and OpenRouter, each ~150–200 lines.
🔍 Zero hidden frameworks — just httpx, pydantic, playwright, and typer.
🔁 Flat prompt → observe → execute script loop — readable end-to-end, easy to debug, easy to fork.
🧪 Run-artifact first — every run writes trajectories and screenshots to disk for inspection.

If you want a minimal, easy-to-debug starting point for browser-using agents instead of another heavyweight platform, this is it.

How they differ at the architectural level:

	Stagehand (Browserbase)	agent-browser (Vercel)	browser-use	Webwright
Paradigm	Hybrid: code + NL primitives (`act` / `extract` / `agent`)	CLI tool that another agent (Claude Code, Codex, etc.) calls	Autonomous LLM agent loop over DOM/AX snapshots	Coding agent with a terminal; browser is just an environment it spawns
Action space	Playwright code, or NL → LLM-translated Playwright	Discrete subcommands (`open`, `click @e2`, `snapshot`, `eval`)	Indexed click/type actions selected by the LLM	Free-form Python (writes Playwright scripts itself)
What is "state"?	The browser session	The browser session (held by daemon across CLI calls)	The browser session	The local workspace — code, screenshots, logs. Browser is disposable.
Loop shape	Imperative; `agent()` does multi-step when needed	One CLI invocation per micro-step	observe → predict next action → execute → repeat	write code → execute → inspect screenshots → repair (code-as-action)

🎥 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

Note: report.json is only generated when -c task_showcase.yaml is included. A plain base.yaml run produces trajectory.json and debug artifacts but no report.json.

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

🧠 Skill Factory (turn solved tasks into runnable code skills)

Most agent skills are context the model reads. Ours are programs. webwright.skill_factory distills the script every solve leaves behind into a growing library of reusable, verified, parameterized skills — code you can run without a model and compose into the next task instead of re-exploring the site. Plugs in with no change to the agent loop:

Reuse — before a solve starts, the library is checked out of the agent loop (recommend): route either runs a matching skill directly (no model) or injects it into the prompt as a prior ({verdict: run|adapt|skip, skill_id, source_path}); the agent reuses the hint without ever querying the library itself.
Grow — afterwards, python -m webwright.skill_factory learn outputs/ --library ./library groups solves of the same template and distills one parameterized skill (build does solve→learn in one shot; update is manual-manifest mode).

Verified twice before it lands: an input gate keeps a wrong solve from ever feeding a skill, and the distilled skill must replay its own answers standalone — no model — so a broken skill can't poison the library. New solves widen a skill in place, regression-replayed so old coverage can't break.

Once learned, a skill runs standalone in ~40 s with zero tokens. On WebArena (10 retrieve-type templates, 3 self-hosted sites, gpt-5.4) reuse lifts held-out accuracy 55% → 70% (+15 pp) while cutting steps. See src/webwright/skill_factory/README.md.

🚀 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

Flag	Description
`-c`	Config file(s) from `src/webwright/config/` (stackable).
`-t`	Task instruction.
`--start-url`	Initial page.
`--task-id`	Output subfolder name.
`-o`	Output directory.

🔌 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

Install

Install through the bundled marketplace inside Claude Code:

# 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

Prefer a local checkout? Point the marketplace command at the cloned repo instead:

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

Use

Start a new Claude Code session after installing — plugins are loaded at session start and won't appear until you restart.

You can either ask Claude Code in plain English (the skill auto-activates from its description), or use one of the slash commands:

/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

/webwright:run (or any plain prompt) produces a one-shot final_script.py for the literal task values.
/webwright:craft produces a reusable CLI tool: final_script.py becomes one parameterized function with a Google-style Args: docstring and an argparse wrapper whose flags default to the concrete task values, so you can rerun it later with different arguments — e.g. python final_script.py --origin JFK --destination LAX --depart-date 2026-07-01.

In both modes Claude Code scaffolds a workspace with plan.md, runs instrumented Playwright scripts under final_runs/run_<id>/, and visually self-verifies each critical point against the saved screenshots.

Install

Codex reads Claude-style marketplaces, so the same repo works as a Codex plugin marketplace. From the Codex CLI:

# 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

Prefer a local checkout?

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

Then restart Codex so the new marketplace and plugin are picked up.

Use

In a new Codex thread, either ask in plain English (the skill auto-activates from its description) or invoke the bundled skill explicitly with @webwright:

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

Codex scaffolds a workspace with plan.md, runs instrumented Playwright scripts under final_runs/run_<id>/, and visually self-verifies each critical point against the saved screenshots.

To turn the plugin off without uninstalling, set its entry in ~/.codex/config.toml to enabled = false and restart Codex.

Install

Install directly from a local checkout (path, archive, npm spec, git repo, or clawhub: spec all work):

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

Verify:

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

Use

The webwright skill is now available to any OpenClaw agent surface (CLI, Telegram, etc.) — invoke it by asking the agent in natural language, or via the slash commands shipped under skills/webwright/commands/, e.g. /webwright run <task>.

To uninstall: openclaw plugins uninstall webwright.

Install

Hermes Agent is a skills-compatible client, so the same skills/webwright/ folder loads as a Hermes skill. Symlink it into your Hermes user-skills directory:

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

No Hermes-specific manifest is needed; only SKILL.md is loaded.

Use

Start Hermes (hermes) and ask it to drive a web task in natural language — the skill auto-activates from its description. You can also invoke it explicitly with /webwright.

Note: the named subcommands shipped under skills/webwright/commands/ (/webwright:run, /webwright:craft) are a Claude Code / Codex convention and are inert in Hermes; the skill itself still works end-to-end.

📃 Trajectory Comparison & Viewer

You can run the same tasks using the Webwright harness and its Codex / GitHub Copilot skill variant, and see how token usage and trajectories stack up between different harnesses. The trajectory viewer supports Codex, GitHub Copilot and Webwright harness traces.

Trajectory comparison

How to use

cd assets/compare_trajectory/
python3 -m http.server

Open the webpage in your browser and upload the Webwright raw_responses.jsonl and attach trajectory.json to view. Then on the other side you can upload your Codex or GitHub Copilot trace.

Obtaining Codex traces:

ls ~/.codex/sessions/2026/MONTH/DAY/SESSION_ID.jsonl

Obtaining GitHub Copilot traces:

/export file session
-> session.md is the uploadable trace

Quick Comparison

"Find the cheapest used 8-cylinder bmw made between 2005-2015 and priced from 25,000 to 50,000 dollars with mileage less than 50,000 miles or less."

Tokens	Webwright Harness (Local Browser Mode)	Codex Webwright Skill
Input	420,433	3,271,143
Output	3,593	20,040
Reasoning	0	4,410
Cached	217,216	3,081,3440
Total	424,026	3,291,183

Individual runs and results may vary.

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}
}

File tree

135

microsoft/WebwrightView on GitHub

.claude-plugin/
  marketplace.json
  plugin.json
.codex-plugin/
  plugin.json
.github/
  workflows/
    skills-tests.yml
.gitignore
assets/
  compare_trajectory/
    app.js
    index.html
    styles.css
  demo.mp4
  odysseys_eval_step100.png
  om2w_autoeval_step100.png
  skill_factory_demo.mp4
  skill_factory_interfaces.png
  skill_factory_interfaces.svg
  skill_factory_pipeline.png
  skill_factory_pipeline.svg
  task_showcase/
    app.py
    README.md
    tasks/
      austin_apartments/
        report.json
        task.json
      driving_weather/
        report.json
        task.json
      nz_au_legal_jobs/
        report.json
        task.json
      ophelia_pittsburgh/
        report.json
        task.json
      pokemon_tcg/
        report.json
        task.json
      slickdeals/
        report.json
        task.json
    templates/
      dashboard.html
      task.html
  trajectory-compare.png
  webwright_logo.svg
CODE_OF_CONDUCT.md
docs/
  skill_factory/
    manual.md
    reference.md
LICENSE
pyproject.toml
README.md
SECURITY.md
skills/
  webwright/
    commands/
      craft.md
      run.md
    reference/
      cli_tool_mode.md
      playwright_patterns.md
      workflow.md
    SKILL.md
src/
  webwright/
    __init__.py
    agents/
      __init__.py
      default.py
    config/
      __init__.py
      base.yaml
      crafted_cli.yaml
      local_browser.yaml
      model_claude.yaml
      model_openai.yaml
      model_openrouter.yaml
      persistent_browser.yaml
      task_showcase.yaml
    environments/
      __init__.py
      local_browser.py
      local_workspace.py
    exceptions.py
    models/
      __init__.py
      anthropic_model.py
      base.py
      openai_model.py
      openrouter_model.py
    run/
      __init__.py
      cli.py
      doctor.py
      run_command.sh
    skill_factory/
      __init__.py
      __main__.py
      build.py
      decide.py
      entry_shim.py
      examples/
        batch.example.json
        flights.skill.yaml
        learned_library/
          what_is_the_earliest_nonstop_flight_from_2c8dab1/
            meta.json
            replays.json
            skill.py
        model_gateway.example.yaml
        README.md
        solve_with_library.sh
        tasks.example.json
        trajectories/
          lax_ord/
            agent_response.json
            final_script.py
            task.json
          README.md
          sea_jfk/
            agent_response.json
            final_script.py
            task.json
          sfo_bos/
            agent_response.json
            final_script.py
            task.json
      execute.py
      fill.py
      gate.py
      init.py
      learn.py
      library.py
      llm.py
      prompt.py
      README.md
      retrieve.py
      route.py
      update.py
    tools/
      __init__.py
      _model_config.py
      image_qa.py
      persistent_local_browser.py
      self_reflection.py
      skill_use.py
    utils/
      __init__.py
      logging.py
      runtime.py
      serialize.py
SUPPORT.md
tests/
  conftest.py
  skill_factory/
    test_build_init.py
    test_entry_shim.py
    test_evolve.py
    test_execute.py
    test_fill.py
    test_gate.py
    test_learn.py
    test_learned_example.py
    test_library.py
    test_llm_env.py
    test_recommend.py
    test_retrieve_decide.py
    test_route.py
  unit/
    test_doctor.py
    test_tool_model_routing.py

More Flows by @microsoft.

VerifiedPlugin

Development

win-dev-skills

A GitHub Copilot, Claude Code, and OpenAI Codex plugin for building native Windows apps with WinUI 3 and the Windows App SDK to cover the end-to-end inner loop: scaffold → design → build → run → test → package → ship.

8 skills

@microsoft

View Plugin

VerifiedPlugin

Development

power-platform-skills

Official agent skills/plugins for Power Platform development by Microsoft.

95 skills

@microsoft

View Plugin

VerifiedPlugin

Development

skillopt

Train agent skills like you train neural networks — with epochs, (mini-)batchsize, learning rates, and validation gates — but without touching model weights.

3 skills

@microsoft

View Plugin

FAQ

webwright is a Claude Code plugin with 1 hand-picked skill for automation work, indexed on Flowy. Install it with the command on its page. It includes webwright. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is 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
How do I install webwright?: Run these in Claude Code: /plugin marketplace add microsoft/Webwright then /plugin install webwright@webwright. Then prompt normally.
Does webwright auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is webwright free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Automation

Plugin

webwright

FLOW.md

microsoft@microsoft

GitHub

Plugin Signal75/100Solid

maintained97

capable29

documented100

adopted80

Install on Claude Code

> /plugin marketplace add microsoft/Webwright
> /plugin install webwright@webwright

Stats

Python HTML Bash Vercel Git

+4 tags

GitHub Playwright Anthropic OpenAI

5,899

Stars

372

Forks

Active

Maintenance

Python

Language

MIT

License

6d ago

Last commit

4mo ago

Created

Repo: microsoft/Webwright

In this plugin

2 commands 1 skill

commands
- craft
- run
skills
- webwright

See everything inside

What's inside

Skills

Commands

/craftCraft a reusable Webwright CLI tool by parameterizing a web task./runRun a one-shot web task with the Webwright Playwright workflow.

README

Read on GitHub

Webwright

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

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

2026-07-21 — Skill Factory: every solve leaves a script behind, distilled into reusable, verified, parameterized code skills that rerun standalone with no model (~40 s, zero tokens). On WebArena, reuse lifts held-out accuracy 55% → 70% (+15 pp). See Skill Factory.
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.

🧱 Robust, reusable interaction with web environments — instead of fragile pixel-level actions, a coding agent with a terminal queries elements, waits for conditions, and handles dynamic behaviors like lazy loading or re-rendering. The resulting scripts can be rerun, adapted, and shared across tasks rather than rediscovered from scratch.
⚡ Efficient composition of complex workflows — multi-step interactions like selecting a date or filling a form become a compact program. Loops, functions, and abstractions let the agent generalize across similar tasks (e.g. different dates) without re-predicting the same low-level sequences. Fewer interaction rounds, faster execution, less error accumulation on long horizons.
🧪 Workspace-as-state, not browser-as-state — the agent can write exploratory scripts, spawn fresh browser sessions, and decide for itself when to capture screenshots and inspect failures, much like a human engineer iterating on an RPA script.
🪄 Surprisingly effective despite being minimal — this stripped-down setup turns out to handle complex and especially long-horizon web tasks well (see Performance).

Most web agent frameworks bury the actual agent loop under layers of abstractions. Webwright takes the opposite stance:

🪶 Lightweight by design — core agent loop in a single ~450-line file, Playwright environment in ~570 lines, CLI in ~150 lines.
🧩 Pluggable model backends — OpenAI, Anthropic, and OpenRouter, each ~150–200 lines.
🔍 Zero hidden frameworks — just httpx, pydantic, playwright, and typer.
🔁 Flat prompt → observe → execute script loop — readable end-to-end, easy to debug, easy to fork.
🧪 Run-artifact first — every run writes trajectories and screenshots to disk for inspection.

If you want a minimal, easy-to-debug starting point for browser-using agents instead of another heavyweight platform, this is it.

How they differ at the architectural level:

	Stagehand (Browserbase)	agent-browser (Vercel)	browser-use	Webwright
Paradigm	Hybrid: code + NL primitives (`act` / `extract` / `agent`)	CLI tool that another agent (Claude Code, Codex, etc.) calls	Autonomous LLM agent loop over DOM/AX snapshots	Coding agent with a terminal; browser is just an environment it spawns
Action space	Playwright code, or NL → LLM-translated Playwright	Discrete subcommands (`open`, `click @e2`, `snapshot`, `eval`)	Indexed click/type actions selected by the LLM	Free-form Python (writes Playwright scripts itself)
What is "state"?	The browser session	The browser session (held by daemon across CLI calls)	The browser session	The local workspace — code, screenshots, logs. Browser is disposable.
Loop shape	Imperative; `agent()` does multi-step when needed	One CLI invocation per micro-step	observe → predict next action → execute → repeat	write code → execute → inspect screenshots → repair (code-as-action)

🎥 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)

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

Note: report.json is only generated when -c task_showcase.yaml is included. A plain base.yaml run produces trajectory.json and debug artifacts but no report.json.

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

🧠 Skill Factory (turn solved tasks into runnable code skills)

Reuse — before a solve starts, the library is checked out of the agent loop (recommend): route either runs a matching skill directly (no model) or injects it into the prompt as a prior ({verdict: run|adapt|skip, skill_id, source_path}); the agent reuses the hint without ever querying the library itself.
Grow — afterwards, python -m webwright.skill_factory learn outputs/ --library ./library groups solves of the same template and distills one parameterized skill (build does solve→learn in one shot; update is manual-manifest mode).

🚀 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

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

Flag	Description
`-c`	Config file(s) from `src/webwright/config/` (stackable).
`-t`	Task instruction.
`--start-url`	Initial page.
`--task-id`	Output subfolder name.
`-o`	Output directory.

🔌 Use as a Plugin

Common runtime deps (install once after either path):

pip install -e .
playwright install chromium

Install

Install through the bundled marketplace inside Claude Code:

# 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

Prefer a local checkout? Point the marketplace command at the cloned repo instead:

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

Use

Start a new Claude Code session after installing — plugins are loaded at session start and won't appear until you restart.

You can either ask Claude Code in plain English (the skill auto-activates from its description), or use one of the slash commands:

/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

/webwright:run (or any plain prompt) produces a one-shot final_script.py for the literal task values.
/webwright:craft produces a reusable CLI tool: final_script.py becomes one parameterized function with a Google-style Args: docstring and an argparse wrapper whose flags default to the concrete task values, so you can rerun it later with different arguments — e.g. python final_script.py --origin JFK --destination LAX --depart-date 2026-07-01.

Install

Codex reads Claude-style marketplaces, so the same repo works as a Codex plugin marketplace. From the Codex CLI:

# 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

Prefer a local checkout?

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

Then restart Codex so the new marketplace and plugin are picked up.

Use

In a new Codex thread, either ask in plain English (the skill auto-activates from its description) or invoke the bundled skill explicitly with @webwright:

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

Codex scaffolds a workspace with plan.md, runs instrumented Playwright scripts under final_runs/run_<id>/, and visually self-verifies each critical point against the saved screenshots.

To turn the plugin off without uninstalling, set its entry in ~/.codex/config.toml to enabled = false and restart Codex.

Install

Install directly from a local checkout (path, archive, npm spec, git repo, or clawhub: spec all work):

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

Verify:

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

Use

To uninstall: openclaw plugins uninstall webwright.

Install

Hermes Agent is a skills-compatible client, so the same skills/webwright/ folder loads as a Hermes skill. Symlink it into your Hermes user-skills directory:

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

No Hermes-specific manifest is needed; only SKILL.md is loaded.

Use

Start Hermes (hermes) and ask it to drive a web task in natural language — the skill auto-activates from its description. You can also invoke it explicitly with /webwright.

📃 Trajectory Comparison & Viewer

Trajectory comparison

How to use

cd assets/compare_trajectory/
python3 -m http.server

Open the webpage in your browser and upload the Webwright raw_responses.jsonl and attach trajectory.json to view. Then on the other side you can upload your Codex or GitHub Copilot trace.

Obtaining Codex traces:

ls ~/.codex/sessions/2026/MONTH/DAY/SESSION_ID.jsonl

Obtaining GitHub Copilot traces:

/export file session
-> session.md is the uploadable trace

Quick Comparison

"Find the cheapest used 8-cylinder bmw made between 2005-2015 and priced from 25,000 to 50,000 dollars with mileage less than 50,000 miles or less."

Tokens	Webwright Harness (Local Browser Mode)	Codex Webwright Skill
Input	420,433	3,271,143
Output	3,593	20,040
Reasoning	0	4,410
Cached	217,216	3,081,3440
Total	424,026	3,291,183

Individual runs and results may vary.

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}
}

File tree

135

microsoft/WebwrightView on GitHub

.claude-plugin/
  marketplace.json
  plugin.json
.codex-plugin/
  plugin.json
.github/
  workflows/
    skills-tests.yml
.gitignore
assets/
  compare_trajectory/
    app.js
    index.html
    styles.css
  demo.mp4
  odysseys_eval_step100.png
  om2w_autoeval_step100.png
  skill_factory_demo.mp4
  skill_factory_interfaces.png
  skill_factory_interfaces.svg
  skill_factory_pipeline.png
  skill_factory_pipeline.svg
  task_showcase/
    app.py
    README.md
    tasks/
      austin_apartments/
        report.json
        task.json
      driving_weather/
        report.json
        task.json
      nz_au_legal_jobs/
        report.json
        task.json
      ophelia_pittsburgh/
        report.json
        task.json
      pokemon_tcg/
        report.json
        task.json
      slickdeals/
        report.json
        task.json
    templates/
      dashboard.html
      task.html
  trajectory-compare.png
  webwright_logo.svg
CODE_OF_CONDUCT.md
docs/
  skill_factory/
    manual.md
    reference.md
LICENSE
pyproject.toml
README.md
SECURITY.md
skills/
  webwright/
    commands/
      craft.md
      run.md
    reference/
      cli_tool_mode.md
      playwright_patterns.md
      workflow.md
    SKILL.md
src/
  webwright/
    __init__.py
    agents/
      __init__.py
      default.py
    config/
      __init__.py
      base.yaml
      crafted_cli.yaml
      local_browser.yaml
      model_claude.yaml
      model_openai.yaml
      model_openrouter.yaml
      persistent_browser.yaml
      task_showcase.yaml
    environments/
      __init__.py
      local_browser.py
      local_workspace.py
    exceptions.py
    models/
      __init__.py
      anthropic_model.py
      base.py
      openai_model.py
      openrouter_model.py
    run/
      __init__.py
      cli.py
      doctor.py
      run_command.sh
    skill_factory/
      __init__.py
      __main__.py
      build.py
      decide.py
      entry_shim.py
      examples/
        batch.example.json
        flights.skill.yaml
        learned_library/
          what_is_the_earliest_nonstop_flight_from_2c8dab1/
            meta.json
            replays.json
            skill.py
        model_gateway.example.yaml
        README.md
        solve_with_library.sh
        tasks.example.json
        trajectories/
          lax_ord/
            agent_response.json
            final_script.py
            task.json
          README.md
          sea_jfk/
            agent_response.json
            final_script.py
            task.json
          sfo_bos/
            agent_response.json
            final_script.py
            task.json
      execute.py
      fill.py
      gate.py
      init.py
      learn.py
      library.py
      llm.py
      prompt.py
      README.md
      retrieve.py
      route.py
      update.py
    tools/
      __init__.py
      _model_config.py
      image_qa.py
      persistent_local_browser.py
      self_reflection.py
      skill_use.py
    utils/
      __init__.py
      logging.py
      runtime.py
      serialize.py
SUPPORT.md
tests/
  conftest.py
  skill_factory/
    test_build_init.py
    test_entry_shim.py
    test_evolve.py
    test_execute.py
    test_fill.py
    test_gate.py
    test_learn.py
    test_learned_example.py
    test_library.py
    test_llm_env.py
    test_recommend.py
    test_retrieve_decide.py
    test_route.py
  unit/
    test_doctor.py
    test_tool_model_routing.py

More Flows by @microsoft.

VerifiedPlugin

Development

win-dev-skills

8 skills

@microsoft

View Plugin

VerifiedPlugin

Development

power-platform-skills

Official agent skills/plugins for Power Platform development by Microsoft.

95 skills

@microsoft

View Plugin

VerifiedPlugin

Development

skillopt

Train agent skills like you train neural networks — with epochs, (mini-)batchsize, learning rates, and validation gates — but without touching model weights.

3 skills

@microsoft

View Plugin

FAQ

What is 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
How do I install webwright?: Run these in Claude Code: /plugin marketplace add microsoft/Webwright then /plugin install webwright@webwright. Then prompt normally.
Does webwright auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is webwright free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.