Top all-time · #14668
Stagehand
Company blog · stagehand.dev/blogaiprogramming
Stagehand is the company blog at stagehand.dev, writing about ai and programming. Since 2025, 5 different Hacker News readers have linked it 7 times, most often “For Computer Use, the harness matters as much as the model”. No feed was found, so read it on the site itself.
Too few sampled comments (5) to say how often HN recommends it.?
Why HN links it
HN readers link Stagehand, an AI layer built on Playwright for browser automation and agent-driven testing, plus its posts on latency and token efficiency. Comments describe use and point to evals and a demo; none judge the writing.
Summarised by Claude from a sample of 5 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Stagehand is the SDK for browser agents. Playwright-style API, self-healing selectors, and TypeScript, Python, and Go, running as an extension inside the browser so remote browsers are as fast as local.
Most-linked posts?
- For Computer Use, the harness matters as much as the model2 people · 3 mentions · first linked 2026-09-18
What Hacker News says?
I tried doing LLM-based tests, coined it "agentic-tests" and it worked quite well: The idea was to use Stagehand [1] as the testing framework and then integrate this with Linear, which is our ticketing system. During a hackathon I whipped something together: first the 'agent' read a UAT from linear, then it pass this into a quite heavily prompted Stagehand. The prompts instructed Stagehand to run the UAT after its b…
Comment linking /
on “A practical guide to building agents [pdf]”Submitted For Computer Use, the harness matters as much as the model as a story · 33 points
HN discussionA lot, especially for performance. That's why we built our own benchmarks that account for both the model and the harness. For example, with Claude Opus 5, the accuracy gap can be up to 3% and performance up to 200ms, depending on whether you're using Deep Agents, Eve, or Fx. More details here: https://www.stagehand.dev/evals
Comment linking /evals
on “We made Playwright 2x faster and 80% more token efficient”Submitted Why Playwright MCP Uses So Many Tokens as a story · 3 points
HN discussionWe built Stagehand 2 years ago (24k stars and 4M monthly npm downloads) and recently fixed its biggest flaw: round-trip latency. Every action performed requires a round trip between your script and the browser (short when running locally but increased when running in the cloud). We also saw multiple posts complaining about the eager token appetite of Playwright MCP. For this reason, we rebuilt Stagehand from the gro…
Comment linking /evals
on “We made Playwright 2x faster and 80% more token efficient”Try https://stagehand.dev/dino ;)
Comment linking /dino
on “For Computer Use, the harness matters as much as the model”Playwright is great. Take a look at Stagehand, it's an AI layer built on top of Playwright: https://www.stagehand.dev (It can run locally.)
Comment linking /
on “Ask HN: Any local agents to help repetitive browser tasks?”