heisen_berg
heisen_berg on Hacker News
You found a fun way, interesting
Posted by
heisen_berg on Tuesday April 07, 2026 @09:00AM
from the show-hn dept.
Hi everyone. AI can generate code in seconds now but verifying and auditing it inside our CI/CD pipelines does not happen at the same speed. It has become a massive bottleneck. To clear this up we just released a GitHub action that we completely open sourced. It basically boots your app in CI opens a real browser tests the PR and if the UI is broken it autonomously pushes a code fix. This...
Great write-up, but looking at the results, it seems the massive 78% token reduction comes primarily from the execute tool batching actions, rather than DevTools being inherently lighter than Playwright. If someone added a similar sandboxed execute tool to Playwright-MCP to allow batching, wouldn't the token usage and turn count be nearly identical? I'm trying to understand if the protocol (CDP) is the real winner here, or just the smart API design of your MCP
Is this project open source? If so, is there any limitation to install any local environment?
Do you offer any on-prem solution?
Very useful to be able to see the details of e2e tests, especially cloud environment. Do you have an on-prem or library solution for running internally?
Localstack is our favorite for developing our application on AWS environment. It saves us from redeploys and AWS env based issues by simulating services on locally