Registry / llm-agents / browsergym-webarena

browsergym-webarena

library0.14.3pypypiunverified

WebArena benchmark environment for BrowserGym, version 0.14.3. Provides a Gymnasium-compatible environment for evaluating web agents on realistic web interaction tasks.

llm-agents testing

pip install browsergym-webarena

github ↗package ↗

INSTALL

IMPORT

SIG · BROWSERGYM-WEBAREN

browsergym-webarena

llm-agentspythonv0.14.3

Install

39.3s avg

Import

—

Disk

724MB

Pass rate

4/ 10

Env Coverage4 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.14.3 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

✕ build_error

✓ 45.7s

py 3.11

✕ build_error

✓ 38.1s

py 3.12

✕ build_error

✓ 32.6s

py 3.13

✕ build_error

py 3.9

✕ build_error

✓ 40.9s

724MB installed

● package 724MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

WebArenaEnv

✓ from browsergym.webarena import WebArenaEnv

✗ from browsergym.webarena import WebArenaEnv

Create a WebArena environment and reset it. Use 'headless=True' for servers.

import gymnasium as gym import browsergym.webarena env = gym.make('browsergym/webarena.0', headless=True) obs, info = env.reset() # run your agent env.close()

Debug

Known issues

breakingWebArena requires a specific Docker image for the websites. The environment will fail to initialize if the Docker containers are not running.

fix

Pull and run the required Docker images as per the WebArena setup instructions before using the environment.

affects: all

deprecatedThe 'browsergym/webarena' environment ID is deprecated in favor of task-specific IDs like 'browsergym/webarena.0'.

fix

Use 'browsergym/webarena.<task_id>' where <task_id> is an integer from 0 to 811.

affects: >=0.14.0

gotchaThe environment returns observations as dictionaries with 'screenshot' (PIL Image), 'text' (str), and other fields. Do not assume it returns a single array.

fix

Always access 'obs['screenshot']' or 'obs['text']' appropriately.

affects: all

gotchaThe environment uses Playwright under the hood. Do not run multiple environments in the same process without proper cleanup, or you may face port conflicts.

fix

Use 'env.close()' after each episode or use context managers.

affects: all

gotchaWebArena tasks are defined with a specific evaluation function (teardown). The agent must return an action string; otherwise, the evaluation may not work correctly.

fix

Ensure your agent returns a string action from the 'action_space' (Text space) each step.

affects: all

Upgrade

Version history

0.14.3latest on PyPI · released Jan 20, 2026

Audit

Dependencies

browsergym-corerequiredCore BrowserGym framework required for all environments

gymnasiumrequiredEnvironment API compatible with Gymnasium

Agent activity

32 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/ServiceNow/BrowserGym ↗

packagehttps://pypi.org/project/browsergym-webarena/ ↗