Plain-English automation
Turn a plain-English objective into browser actions without writing selectors or page-object code. The examples show tasks like logging in, adding an item to cart, and verifying a result.
BrowserBash
BrowserBash is a natural-language browser automation CLI for running browser tasks and tests from the command line. It supports local Chrome, CDP endpoints, and cloud browser providers, with a free open-source path and no API keys required to start.
Natural-language browser automation from the CLI
BrowserBash is a natural-language browser automation CLI for running browser tasks and tests from the command line. It turns a plain-English objective into real browser actions, using a browser provider, an execution engine, and a language model chosen from the supported options.
The product is built around a free open-source path: the CLI, a local dashboard, and a cloud account are available at no cost, with no API keys required to get started. It can run locally in Chrome, connect to a CDP endpoint, or use cloud browser providers, and it supports recording, dashboard replay, and CI-friendly output for testing workflows.
Features
Markdown test files
Save scenarios as readable `*_test.md` files and compose shared setup with `@import`. The site also describes result output written after each run.
Multiple browser providers
Run against local Chrome, any CDP endpoint, or cloud providers including Browserbase, LambdaTest, and BrowserStack. The same test file can be used across different browser targets.
Free model options
Use free local models through Ollama or free models on OpenRouter with zero API keys. Optional Anthropic or OpenRouter keys can be supplied if you want to swap models.
Agent and CI output
Stream one JSON event per line for tools and agents, with CI-friendly exit codes `0/1/2/3`. The product also includes session recording with video and screenshots.
Common use cases
Browser tests in natural language
Write a short plain-English test file for a browser flow, then run it from the CLI and review the result file or dashboard replay.
Cross-provider automation
Run the same objective against local Chrome during development and a cloud browser provider in another environment, without changing the test intent.
CI gating for browser checks
Use the `--agent` NDJSON stream and exit codes in CI so pipelines can treat a browser run as a pass, fail, error, or timeout signal.
Session recording and debugging
Capture video and screenshots with `--record` when you need a replayable record of what happened during a run.
Secret-safe browser runs
Keep credentials out of logs by templating variables and marking secrets so they are masked in output and summaries.
Pros and Cons
Pros
- Free open-source CLI with no credit card required to start.
- Supports local Chrome, CDP endpoints, and several cloud browser providers.
- Can use free local or hosted models, including an API-key-free path.
- Produces CI-friendly NDJSON output and structured exit codes.
- Includes local and cloud dashboards, plus session recording for replay.
Cons
- The feature set on the site is focused on browser automation and testing; it does not present broader workflow or team-management features.
- Extended cloud run retention is listed as coming soon, so the free 15-day history is the current default cloud retention window.
FAQ
Is BrowserBash free to use?
Yes. BrowserBash says the CLI, local dashboard, and free cloud account cost nothing, and there is no credit card required to install or sign up. The paid option is optional extended cloud run retention beyond the free 15-day window.
Do I need an API key?
No. The product is designed to run on free local models through Ollama or free models on OpenRouter, so you can automate without API keys. You can also bring your own Anthropic or OpenRouter key if you want to.
How does BrowserBash fit into a test workflow?
You can write committable `*_test.md` files, run them from the CLI, and get NDJSON output plus CI exit codes. The case study also shows a recorded session and dashboard replay after running with `--record` and `--upload`.
What kind of dashboard does it provide?
BrowserBash supports a local dashboard on your machine and a free cloud dashboard for uploaded runs. The cloud view includes run history, recordings, and per-run replay.
Can I use BrowserBash commercially?
BrowserBash is open source under Apache-2.0 and the site says it can be used commercially, including at work and in CI. The source also says free runs are kept for 15 days unless extended retention is added later.
Quick Facts
- Category
- Developer Tool
- Product type
- Browser automation CLI
- Primary workflow
- Plain-English browser tests and automation
- License
- Apache-2.0
- Source domain
- browserbash.com
- Pricing
- Free core product; optional paid cloud retention
Alternative a BrowserBash
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Manta AI
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
SonOf
SonOf connects to your repo and PM tool, audits the codebase and surrounding product context, and turns approved work into shipped tickets with senior engineering review. It is aimed at founders and engineering leaders who need backlog help without hiring a full team immediately.
Ghost
Ghost è un assistente AI da terminale per chattare, generare codice ed eseguire task da riga di comando. Include modelli gratuiti, supporta Linux, macOS e Windows, ed è open source.