Playwright CLI
Hacker ApprovedRanked 2 of 12 browser automation tools by recommenders
Lets coding agents and developers drive a browser from the command line, token-efficient and working out of the box with essentially zero setup.
Lets coding agents and developers drive a browser from the command line, token-efficient and working out of the box with essentially zero setup.
20 people gave an opinion
- recommend it
- 19
- criticize it
- 1
- approval share
- 95%
Recommended in 5 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 19 people recommend itNeeds 10 or more, met.
- 19 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 5 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Lighter on tokens than MCP
“token efficient, fast and more customizable/upgradable based on your workflow”
Comment from 16 Mar 2026 in “Let your Coding Agent debug the browser session with Chrome DevTools MCP” “Playwright-cli (not mcp) is so much more efficient.”
Comment from 24 Mar 2026 in “Show HN: ProofShot – Give AI coding agents eyes to verify the UI they build” “the CLI + skill is much lighter on token usage”
Comment from 19 Feb 2026 in “Tell HN: OpenCode/Claude Code and Playwright CLI is great for front end dev” - Comment from 15 Mar 2026 in “Let your Coding Agent debug the browser session with Chrome DevTools MCP”
Faster and less buggy than MCP
“It works much faster for me than the MCP servers I tried.”
Comment from 3 Jul 2026 in “The Safari MCP server for web developers” “faster and less buggy than the MCP”
Comment from 3 Jul 2026 in “The Safari MCP server for web developers” Works out of the box
“highly effective for debugging locally deployed web apps with essentially zero setup”
Comment from 5 May 2026 in “Computer Use Is 45x More Expensive Than Structured APIs” “playwright-cli works out of the box”
Comment from 9 Mar 2026 in “Agent Safehouse – macOS-native sandboxing for local agents” Inspects DOM and simulates clicks
“Your agent can use it to inspect the DOM, see what styles are applied to elements, simulate clicks, etc.”
Comment from 12 Apr 2026 in “Why AI Sucks at Front End” “Playwright cli gives you basically all of this without writing any glue code.”
Comment from 25 Mar 2026 in “Show HN: ProofShot – Give AI coding agents eyes to verify the UI they build”
What people warn about
Each mark is one comment
Token savings only when bytes stay out of context
“the savings only come in cases when you don't need the bytes in context”
Comment from 25 Feb 2026 in “I made MCP cheaper in one command”
Other browser automation tools people recommend
The four most recommended other browser automation tools, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Playwright | 137 | 28 | 83% | 12 | 3 mo3 owners | Approved |
| Playwright CLIThis page | 19 | 1 | 95% | 5 | — | Approved |
| Selenium | 15 | 5 | 75% | 5 | — | Approved |
| Puppeteer | 14 | 16 | 47% | 10 | — | — |
| Stagehand | 13 | 2 | 87% | 7 | — | Approved |
What people said
21 of the 24 comments that mention it, newest first. Each links to the original comment.
“with playwright-cli, the agent makes reasoning decisions between each cli call”
“faster and less buggy than the MCP”
“It works much faster for me than the MCP servers I tried.”
“highly effective for debugging locally deployed web apps with essentially zero setup”
“You need to do a lot of post-processing on it to get it to be a reliable automation.”
“Your agent can use it to inspect the DOM, see what styles are applied to elements, simulate clicks, etc.”
“So I switched to playwright cli”
“The only skill you should probably install instead of maintaining it yourself is playwright-cli”
“Playwright cli gives you basically all of this without writing any glue code.”
“playwright-cli and agent-browser are much much better”
“Playwright-cli (not mcp) is so much more efficient.”
“is local and without external dependencies on even more third parties”
“token efficient, fast and more customizable/upgradable based on your workflow”
“a skill with playwright cli in headless mode is much more effective”
“more token-efficient than using the raw mcp”
“playwright-cli works out of the box”
“Which has been playing much nicer so far.”
“A very good example of this is playwright-cli vs Playwright MCP”
“the savings only come in cases when you don't need the bytes in context”
“the CLI + skill is much lighter on token usage”
“Yeah that's an excellent option for this kind of thing too.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.