🛠️ Hacker News Tools

[Testing] Show HN: Resurf – realistic, reproducible test framework for AI browser agents Systematic testing of browser agents today is not easy: testing on real websites is flaky, rate-limited and potentially expensive (e.g. using proxies or bypassing Captcha), while static-HTML benchmarks lack state and dynamic behavior.<p>Resurf gives your browser agent a realistic, stateful, instrumented framework — built on synthetic websites with failure-mode injection:<p>- Realistic, dynamic, interactive environment - Deterministic &amp; reproducible - Failure-mode injection (latency, payment errors, 5xx) - Auditable success eval (DB state, not LLM judge) - No dependency on live websites - Browser Use and Stagehand supported out of the box

[Other] Cloudflare to cut about 20% workforce <a href="https:&#x2F;&#x2F;blog.cloudflare.com&#x2F;building-for-the-future&#x2F;" rel="nofollow">https:&#x2F;&#x2F;blog.cloudflare.com&#x2F;building-for-the-future&#x2F;</a>

[Other] Natural Language Autoencoders: Turning Claude's Thoughts into Text

[Other] Principles for agent-native CLIs

[Other] Hardening Firefox with Claude Mythos Preview <a href="https:&#x2F;&#x2F;arstechnica.com&#x2F;information-technology&#x2F;2026&#x2F;05&#x2F;mozilla-says-271-vulnerabilities-found-by-mythos-have-almost-no-false-positives&#x2F;" rel="nofollow">https:&#x2F;&#x2F;arstechnica.com&#x2F;information-technology&#x2F;2026&#x2F;05&#x2F;mozil...</a>

[CLI Tool] Show HN: Stage CLI – an easier way of reading your AI generated changes locally Hey HN! We&#x27;re Charles and Dean. A few weeks ago we posted about Stage, a code review tool that guides you through reading a PR step by step - <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=47796818">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=47796818</a>.<p>We got a lot of great feedback but also heard from many people that they wanted to have the chapters experience even before opening a PR… so we built the Stage CLI as the local, open-source version that anyone can try.<p>Here’s a quick demo video: <a href="https:&#x2F;&#x2F;www.tella.tv&#x2F;video&#x2F;stage-cli-demo-f55q" rel="nofollow">https:&#x2F;&#x2F;www.tella.tv&#x2F;video&#x2F;stage-cli-demo-f55q</a><p>It works with any coding agent of your choice. The skill instructs the agent to read your current branch’s changes, break them down into separate logical chapters, and open them in a local browser.<p>We’ve found that reading changes this way is a lot easier for us than reading them in an IDE or other similar CLI tools, which present diffs to you in repository tree order. You can see a few examples of what it feels like here: <a href="https:&#x2F;&#x2F;stagereview.app&#x2F;explore">https:&#x2F;&#x2F;stagereview.app&#x2F;explore</a>.<p>Try it out and let us know what you think! Would love to hear any feedback :)

[Other] AlphaEvolve: Gemini-powered coding agent scaling impact across fields

[Other] Idempotency is easy until the second request is different

[Other] Agent-harness-kit scaffolding for multi-agent workflows (MCP, provider-agnostic)

[Other] Show HN: SereneUI – A VSCode-inspired, open-source UI for Postgres

[Other] Show HN: Trust – Coding Rust like it's 1989

[Other] The surprisingly complex journey to text-selectable client-side generated PDFs

[DevOps] Show HN: Kstack – Skill pack for monitoring/troubleshooting K8s in Claude Code Hi All,<p>Recently I&#x27;ve been using Claude Code a lot for debugging cluster issues and I realized I was performing similar tasks repeatedly so I decided to package them up into skills so I could call them up more easily (e.g. `&#x2F;investigate`, `&#x2F;audit-security`, `&#x2F;audit-outdated`). I&#x27;m calling the skill pack &quot;kstack&quot; and the goal is to be able to monitor and troubleshoot K8s from within Claude Code.<p>If you have time, I&#x27;d love to get some feedback on the project!<p>Andres<p>Source: <a href="https:&#x2F;&#x2F;github.com&#x2F;kubetail-org&#x2F;kstack" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;kubetail-org&#x2F;kstack</a><p>Docs: <a href="https:&#x2F;&#x2F;kstack.sh&#x2F;" rel="nofollow">https:&#x2F;&#x2F;kstack.sh&#x2F;</a>

[Other] Building the TD4 4-Bit CPU

[Other] ProgramBench: Can Language Models Rebuild Programs from Scratch?

[API/SDK] Show HN: I Replaced React in GraphiQL with Svelte I love Svelte and GraphQL. I do not like React. So, when I&#x27;m building APIs, I cringe when using the official GraphiQL interface.<p>I have free will and a Claude subscription so I made it happen. You can find it on npm as &quot;@eeeooolll&#x2F;graphiql&quot; (@eol was taken).<p><a href="https:&#x2F;&#x2F;www.npmjs.com&#x2F;package&#x2F;@eeeooolll&#x2F;graphiql" rel="nofollow">https:&#x2F;&#x2F;www.npmjs.com&#x2F;package&#x2F;@eeeooolll&#x2F;graphiql</a><p>I also upgraded my batteries-included GraphQL server to use it. You can find it on JSR.<p><a href="https:&#x2F;&#x2F;jsr.io&#x2F;@eol&#x2F;gq" rel="nofollow">https:&#x2F;&#x2F;jsr.io&#x2F;@eol&#x2F;gq</a>

[Other] Show HN: Dreamwork – a job search site I made after Indeed fired my pregnant wif Hey, I’m Colin and I have a fun story for you.<p>My 7 month pregnant wife was laid off from Indeed (she was a PM there) back in December. This pissed me off quite a bit, as she was supposed to get 6 months leave and instead got fired.<p>So I spent the last five months working part time to build Dreamwork, a platform aiming to make the job search experience actually better with AI (not just mass application spam).<p>I started with just a telegram bot doing scraping, then advanced to Google Embeddings 2.0 for vectorizing the jobs, built out a tight 6 axis scorecard for both the user and each job.<p>Then I actually got to use my English degree (lol) to optimize the prompt for custom per-job resumes and cover letters to make them not sound like - again - shitty AI.<p>Most AI cover letters have a kind of consistently dead quality. They use all the keywords and somehow communicate nothing. I absolutely hate that, so I’ve been fairly obsessive about making the output feel more like a decent human draft: specific but restrained, and not stuffed with keywords.<p>It is now useful enough that I think strangers can try it and find serious value.<p>What it does today:<p>- indexes ~100k curated tech jobs<p>- tries to avoid stale&#x2F;duplicate aggregator garbage<p>- uses semantic matching instead of only keyword search<p>- generates an “application pack” for each job: tailored resume, cover letter, and answers to common&#x2F;custom questions<p>- lets the user edit everything before applying<p>- helps keep track of saved jobs and generated materials<p>Auto apply is the part I’m conflicted about. I do t think blindly spraying applications is good for the candidates (chance of hiring is already low, even with hard work and customization), recruiters (they’re swamped), or the world (we don’t need more slop).<p>I’ll build auto apply out in some format, but I want to be thoughtful about it.<p>I also built out a whole research section to map out layoffs and hiring trends. This will start to be super useful in a month or two.<p>Anyways - it’s all free to use right now. Built originally out of spite, now becoming a real product.<p>I’d love to get feedback on what elements would truly make this the career companion you’re looking for. Not - resume spray and pray platform, but something that will actually help you navigate this insane hiring economy we’re in.<p>You can check it out here:<p><a href="https:&#x2F;&#x2F;dreamworkhq.com" rel="nofollow">https:&#x2F;&#x2F;dreamworkhq.com</a>

[Other] Show HN: Free tool to mark points and polygon regions For a game I&#x27;m developing I needed an easy way to create hotspot areas on images. So I hacked together a small tool to do so and before I knew it, I had created an entire app :-)<p>It allows you to generate JSON or YAML from the coordinates you tack on the image. tack runs entirely in your browser, there is no server side component to it, so good in terms of privacy.<p>Hope this is helpful.

[Other] Apple is enforcing an old App Store rule against a new kind of software

[Other] Show HN: I built a game where AI agents compete to ship code