BrowserBash logo

BrowserBash

Freemium
Visita

BrowserBash trasforma obiettivi in linguaggio naturale in azioni nel browser, con test Markdown, output CI strutturato e un'opzione gratuita con modelli locali senza chiavi API.

Cos'è BrowserBash?

BrowserBash is a natural-language browser automation CLI for running browser tasks and tests from plain English. It turns an objective into real browser actions, then returns structured output that can be consumed by CI systems and other automation tools.

The product is built around an open-source CLI, Markdown-based test files, and support for real browsers on local machines or supported cloud grids. The source emphasizes a free default path with local models, no required API keys, and optional dashboard and cloud features for run history and replay.

Cosa può fare BrowserBash?

Plain-English objectives

Describe a browser task in plain English, and BrowserBash turns it into real browser actions without writing selectors or page-object code.

Markdown test files

Store scenarios in committable `*_test.md` files, reuse flows with `@import`, and template values with variables for repeatable tests.

Free model support

Run on free local models through Ollama or free OpenRouter models without API keys, with optional support for your own Anthropic or OpenRouter key.

Multiple browser providers

Drive local Chrome, any CDP endpoint, or cloud grids such as Browserbase, LambdaTest, and BrowserStack from the same objective.

Agent and CI output

Stream one JSON event per line in NDJSON format and use clean exit codes so agents and CI systems can read the result directly.

Recording and replay

Capture video and screenshots with `--record`, then view runs in a local dashboard or a free cloud dashboard with replay and history.

Casi d'uso

“CI regression testing”

Write end-to-end browser checks as readable Markdown files, then run them in CI with exit codes that indicate pass, fail, error, or timeout.

“Routine browser tasks”

Automate login, checkout, scraping, and other browser workflows by describing the objective in plain English instead of scripting selectors.

“Debugging and replay”

Capture video and screenshots for a run, then replay the session in the dashboard when a step fails or you need a shareable record.

“Private local automation”

Run browser automation locally with Ollama when you want to avoid API keys and keep the session on your machine.

“Cross-provider test runs”

Point the same test file at a local browser or a cloud grid when your team needs to move between laptop runs and hosted infrastructure.

Domande frequenti

What does BrowserBash do?

BrowserBash is designed to automate browser tasks from plain English. The source shows it can run objectives such as logging in, adding items to a cart, scraping text, and running Markdown-based tests, then returning structured output and an exit code.

How do I get started?

The source says you can install the CLI with npm, run it with local Chromium or another supported browser provider, and use a free local model through Ollama. A cloud dashboard account is optional for run history and replay.

Is BrowserBash free?

Yes. The pricing page says the CLI, local dashboard, and a cloud account are free, with no credit card required. It also says the only optional paid item is extended cloud data retention beyond the free retention window, which is coming soon.

Do I need an API key to use it?

BrowserBash supports free local models through Ollama and free OpenRouter models with no API keys required. You can also bring your own Anthropic or OpenRouter key, and the source mentions any OpenAI-compatible server such as vLLM or LM Studio.

Can I use BrowserBash in commercial or CI workflows?

The source says BrowserBash is open source under Apache-2.0. It can be used commercially, and the CLI is positioned for CI because it emits NDJSON events and uses exit codes to signal pass, fail, error, or timeout.

Informazioni rapide

Category
Developer Tool
Primary interface
CLI
Automation style
Natural-language browser automation
License
Apache-2.0
Default model path
Local Ollama models
Source domain
browserbash.com

Analisi del traffico di BrowserBash

I dati sul traffico sono solo a scopo di riferimento.

Domain Rating
3

Alternative a BrowserBash

NxCode logo

NxCode

nxcode.io

NxCode trasforma idee in linguaggio naturale in app full-stack, con test, deployment e piani da 5 $ al mese.

Bugster logo

Bugster

bugster.dev

Piattaforma cloud di test end-to-end con AI e linguaggio naturale

Manta AI logo

Manta AI

mantaai.co

Manta AI è uno strumento autonomo per testare le app web: esegue il crawling di un’app partendo da un URL, mappa i flussi e segnala automaticamente i comportamenti anomali. Genera piani di test in linguaggio naturale per i team che sviluppano prodotti web.

Experiential Labs logo

Experiential Labs

www.experientiallabs.ai

Experiential Labs è un gateway AI open source che offre ai team un unico endpoint e una chiave API per modelli ospitati, chiavi di proprietà dei clienti e modelli locali o personalizzati. Include anche routing, budget, controllo degli accessi, attribuzione e funzionalità di intelligence opzionali per il traffico degli agenti.

Murmell logo

Murmell

murmell.com

Murmell è una tela accessibile dal browser per eseguire agenti di programmazione AI in sandbox cloud condivise. Permette agli sviluppatori di coordinare Claude Code, Codex, Kimi e OpenCode su un unico progetto, senza configurazioni locali né conflitti tra file.

CowCo logo

CowCo

cowco.app

CowCo è un editor nel browser per progetti e file locali, pensato per lavorare con agenti AI senza caricare i file sul cloud.