#playwright

2026-09-19 missarii/Web-Pilot B WebPilot is a local-first AI browser agent that converts natural-language instructions into safe, structured browser actions, navigates websites through Playwright, extracts useful information, semantically filters results, and downloads permitted resources. WebPilot aims to be a self-hosted personal web assistant

2026-10-03 0xgetz/xai-account-setup D A focused Playwright helper for setting up one xAI account and creating one API key.

2026-10-19 dmoka/quicke2e 未评级 Plain-English end-to-end tests for web apps. A small decision model picks each click; code decides pass or fail; a passing run exports a Playwright spec.

2026-10-16 iamumeransari/claude-show-your-work 未评级 Claude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows.

2026-10-16 solari-sdk/solari-cookbook 未评级

2026-09-29 Show HN: Assay – a QA CLI that finds bugs with no LLM and no tests written 未评级 I've always found it odd there was no deterministic QA tools with zero baseline needed, especially after so long. It's always been either (1) playwright or cypress that require written tests, dependant on the tests YOU write, or (2), asking the LLM to find and test bugs in your code, which has 2 cons, its costly (sometimes), and its non-deterministic. That's why i built assay. Its only dependencies is playwright & chromium, and you point it at any folder with a webpage and it runs tests on its own by driving the webpage itself in a browser and clicking every control. It then flags anywhere the webpage contradicted/disagreed with itself; it doesn't know right from wrong NOR what the webpage is about, but universally, a page disagreeing with itself is almost always a bug. An example of this is on a paint app, if you draw two strokes on a canvas and click undo twice, you expect them both to undo each stroke sequentially; in one of 225 benchmarks, clicking the undo the first time didn't remove the first stroke, and only the 2nd click worked. assay drove that and caught it. As for benchmarks, there are 2 variants that are all reproducible in the repo. The first is 225 generated web pages that were first checked by hand, then had assay run on them. There was a total of 20 bugs across all programs, and assay caught 15 with the right reasoning, and had 0 false failures. The second was a harder one where an LLM planted 5 bugs across 10 working original webpages. assay found 12 of the 50 and had 0 false failures, which may seem low, but assays superpower is that its cheap and quick. assays median runtime is 14s, and it plugs into 15 agentic coding harnesses with a skill, plus claude code and deepseek harness have their own plugin that automatically runs it with a stop hook every time the LLM touches a webpage. My favourite feature is that it groups flagged tests together if their of the same bug. More details are in the repo about this since this is getting a little long, but the links it makes have its own benchmarks, 51/51 links it got right with 0 false links. This serves as additional context to you, if you use it as a raw cli, or to your agent if your using it with an LLM harness. pip install assay-ui. All alternative methods to install are on the github, including harness support.

2026-09-15 Show HN: Biloba: fast and stable Chrome-based browser tests in Go and Vitest 未评级 I wrote Ginkgo and Gomega over a decade ago. Biloba's the browser-testing library I've always wanted. It's 2-3x faster than playwright and allows you to write expressive parallelizable browser tests and automations in Ginkgo and Gomega (for Go) and Vitest (for TypeScript). Pragmatic atomic Javascript operations (b.Click("#foo") => foo.click()) give you speed and stability by trading off realism. Opting back into realism (scroll then emit pointer click event) where you need it is as easy as b.Realistic().Click("#foo"). And it's designed from the ground-up to be agent-friendly. Failure messages include DOM outlines, paths to saved screenshots, and polling traces so agents can pinpoint failures quickly. Visual regression tests produce diff images and textual descriptions that point agents at what changed. A set of Claude Code skills describes best practices for finding and eliminating flakes, and keeping them gone. Performance numbers: https://github.com/onsi/biloba?tab=readme-ov-file#performanc... Docs: https://github.com/onsi/biloba?tab=readme-ov-file#performanc...

2026-09-05 alphaparkinc/genpark-multi-step-web-form-fill-orchestrator-skill 未评级 Multi-step web form fill orchestrator with validation (Playwright / Puppeteer)

2026-09-05 alphaparkinc/genpark-spa-network-idle-settlement-waiter-skill 未评级 SPA network idle & DOM mutation settlement waiter (Cypress / Playwright)

2026-09-02 alphaparkinc/genpark-dynamic-browser-stealth-fingerprint-randomizer-skill 未评级 Dynamic browser stealth fingerprint randomizer (Stealth Playwright style)

2026-08-31 alphaparkinc/genpark-dynamic-browser-sandbox-e2e-tester-skill 未评级 Dynamic browser sandbox E2E test synthesizer & HAR verifier (Playwright style)

2026-08-29 Checkly 未评级 Code-first synthetic monitoring for modern DevOps. Monitor your APIs and apps at a fraction of the price of legacy providers. Powered by a Monitoring as Code workflow and Playwright. Generous free tier for devs.