Free, open-source CLI that turns one plain-English sentence into a real browser test — no selectors, no code, no flaky locators. Runs on free local models (Ollama) or free OpenRouter models, so there are zero API keys and no credit card. Works with local Chrome, LambdaTest, BrowserStack, Browserbase or any CDP endpoint. `npm install -g browserbash-cli` and automate any site in seconds. Apache-2.0.
Hey Product Hunt — Pramod here (I run The Testing Academy on YouTube).
Every test-automation tool I picked up meant brittle selectors, flaky locators, and a framework to babysit. I just wanted to *say* what to test and have it happen. So I built BrowserBash: you give it one plain-English objective and an AI agent drives a real browser to do it — no selectors, no code.
What I care about most: it's genuinely free and open source (Apache-2.0). It runs on free local models (Ollama) or free OpenRouter models — zero API keys, no credit card. `npm install -g browserbash-cli` and you're automating any site in seconds. It works with local Chrome, LambdaTest, BrowserStack, Browserbase, or any CDP endpoint. Bring your own Anthropic/OpenRouter key only if you want to.
A free account adds a dashboard with run history, video recordings and per-run replays — so you can see exactly what the agent did.
It's early and I'd genuinely love your honest feedback — what's the first flow you'd point it at, and what would make it a daily driver for you? Roast it if it deserves it. I'm here all day.
Looks awesome, can't wait to try this out! How does this differ from stagehand?
The hard part in plain-English browser tests is preserving intent after selectors change. A good test should explain the user-level invariant it protects, not just regenerate clicks.
Really interesting project! 🚀
The idea of describing a test instead of writing selectors is compelling, especially for quickly validating user flows.
I'm curious: if the UI changes significantly between releases, how does BrowserBash decide whether it's the same workflow with a different layout versus an actual regression that should fail the test?
We've gone from writing tests to describing tests. At this rate the browser is going to start filing bug reports against itself.
Love that it supports local models via Ollama right out of the box so we don't burn through API credits testing basic flows. Going to point this at my onboarding sequences today!
About BrowserBash on Product Hunt
“CLI that turns plain-English into real browser tests”
BrowserBash launched on Product Hunt on June 25th, 2026 and earned 89 upvotes and 17 comments, placing #20 on the daily leaderboard. Free, open-source CLI that turns one plain-English sentence into a real browser test — no selectors, no code, no flaky locators. Runs on free local models (Ollama) or free OpenRouter models, so there are zero API keys and no credit card. Works with local Chrome, LambdaTest, BrowserStack, Browserbase or any CDP endpoint. `npm install -g browserbash-cli` and automate any site in seconds. Apache-2.0.
BrowserBash was featured in Developer Tools (515.5k followers), Artificial Intelligence (473.1k followers) and GitHub (41.3k followers) on Product Hunt. Together, these topics include over 204.8k products, making this a competitive space to launch in.
Who hunted BrowserBash?
BrowserBash was hunted by Prrammod Dutta. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how BrowserBash stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Prrammod Dutta