🛠️ All DevTools

[Other] Show HN: Robust LLM Extractor for Websites in TypeScript We&#x27;ve been building data pipelines that scrape websites and extract structured data for a while now. If you&#x27;ve done this, you know the drill: you write CSS selectors, the site changes its layout, everything breaks at 2am, and you spend your morning rewriting parsers.<p>LLMs seemed like the obvious fix — just throw the HTML at GPT and ask for JSON. Except in practice, it&#x27;s more painful than that:<p>- Raw HTML is full of nav bars, footers, and tracking junk that eats your token budget. A typical product page is 80% noise. - LLMs return malformed JSON more often than you&#x27;d expect, especially with nested arrays and complex schemas. One bad bracket and your pipeline crashes. - Relative URLs, markdown-escaped links, tracking parameters — the &quot;small&quot; URL issues compound fast when you&#x27;re processing thousands of pages. - You end up writing the same boilerplate: HTML cleanup → markdown conversion → LLM call → JSON parsing → error recovery → schema validation. Over and over.<p>We got tired of rebuilding this stack for every project, so we extracted it into a library.<p>Lightfeed Extractor is a TypeScript library that handles the full pipeline from raw HTML to validated, structured data:<p>- Converts HTML to LLM-ready markdown with main content extraction (strips nav, headers, footers), optional image inclusion, and URL cleaning - Works with any LangChain-compatible LLM (OpenAI, Gemini, Claude, Ollama, etc.) - Uses Zod schemas for type-safe extraction with real validation - Recovers partial data from malformed LLM output instead of failing entirely — if 19 out of 20 products parsed correctly, you get those 19 - Built-in browser automation via Playwright (local, serverless, or remote) with anti-bot patches - Pairs with our browser agent (@lightfeed&#x2F;browser-agent) for AI-driven page navigation before extraction<p>We use this ourselves in production at Lightfeed, and it&#x27;s been solid enough that we decided to open-source it.<p>GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;lightfeed&#x2F;extractor" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;lightfeed&#x2F;extractor</a> npm: npm install @lightfeed&#x2F;extractor Apache 2.0 licensed.<p>Happy to answer questions or hear feedback.

[Other] Show HN: Nit – I rebuilt Git in Zig to save AI agents 71% on tokens

[Other] Technology: The (nearly) perfect USB cable tester does exist

[Other] Show HN: A plain-text cognitive architecture for Claude Code

[Other] Show HN: Automate your workflow in plain English operator23 lets non-technical operators describe a workflow in plain English and run it across their tool stack, hubspot, apollo, monday, google drive and others. no builder, no if-then config, just a description and a review step before anything runs.<p>We talked to marketing ops people recently to validate whether we are solving the right problems. Three things came up every single time.<p>Setup complexity. People are not afraid of automation in theory. They are afraid of spending two hours configuring conditions and field mappings, only to have something silently misroute. The config layer is where confidence dies.<p>Debugging. When a workflow breaks there is usually no explanation. A trigger did not fire, data passed null downstream, a sequence stopped. You find out three weeks later when someone downstream asks a question. Nobody knows where it went wrong so they delete it and go back to doing it manually.<p>No trust without control. Everyone wanted to keep a review step before the system acts on its own. Not forever, but until it had proven itself across enough edge cases. The unlock for automation adoption is not fewer steps, it is making it safe to delegate gradually.<p>What we are building is a system that addresses all three. Plain English input so setup is fast, step-by-step explanations so debugging is readable, and staged autonomy so trust is earnable.<p>For founders who have built or managed GTM and marketing ops teams: does this match what you have seen. And is there a fourth problem we are missing.

[DevOps] Show HN: Druids – coordinate and deploy coding agents across machines

[Other] Updates to GitHub Copilot interaction data usage policy

[Other] 90% of Claude-linked output going to GitHub repos w <2 stars

[Other] A single-file C allocator with explicit heaps and tuning knobs

[Other] Show HN: I built an integration for RL training of browser agents for everyone This integration allows for scalable evals and training of browser agents with hosted Prime Intellect eval + training pipelines and headless browser infrastructure on Browserbase to RL train browser agents with LoRA.

[DevOps] Show HN: Optio – Orchestrate AI coding agents in K8s to go from ticket to PR I think like many of you, I&#x27;ve been jumping between many claude code&#x2F;codex sessions at a time, managing multiple lines of work and worktrees in multiple repos. I wanted a way to easily manage multiple lines of work and reduce the amount of input I need to give, allowing the agents to remove me as a bottleneck from as much of the process as I can. So I built an orchestration tool for AI coding agents:<p>Optio is an open-source orchestration system that turns tickets into merged pull requests using AI coding agents. You point it at your repos, and it handles the full lifecycle:<p>- Intake — pull tasks from GitHub Issues, Linear, or create them manually<p>- Execution — spin up isolated K8s pods per repo, run Claude Code or Codex in git worktrees<p>- PR monitoring — watch CI checks, review status, and merge readiness every 30s<p>- Self-healing — auto-resume the agent on CI failures, merge conflicts, or reviewer change requests<p>- Completion — squash-merge the PR and close the linked issue<p>The key idea is the feedback loop. Optio doesn&#x27;t just run an agent and walk away — when CI breaks, it feeds the failure back to the agent. When a reviewer requests changes, the comments become the agent&#x27;s next prompt. It keeps going until the PR merges or you tell it to stop.<p>Built with Fastify, Next.js, BullMQ, and Drizzle on Postgres. Ships with a Helm chart for production deployment.

[Other] .apks are just .zips; semi-legally hacking software for orphaned hardware [video]

[Other] Building a coding agent in Swift from scratch

[Other] Building a Mostly IPv6 Only Home Network

[Build/Deploy] Show HN: CI/CD in your terminal, zero YAML We&#x27;re two engineers that got fed up with context switching. Why do we need to do a git push, open a browser tab, wait for some task to actually start, bite nails (or read HackerNews) for 10 minutes or more while dependencies are being installed for the 100th time and finally end up with an invalid YAML error. And for some reason this usually happens in the final stage of the pipeline leading up to the inevitable git commits &quot;Fixed&quot;, &quot;Fixed again&quot;, &quot;Test&quot;, &quot;Really fixed this time&quot;. We can do better.<p>We set out to build Zippy. A CI&#x2F;CD system that works from your terminal. No context switching, no slow containers, instant feedback and seamless Claude Code integration. Just git push, instant build, and move on. Two bash scripts, one to setup the (cached) environment, one to run the build process.

[Other] TurboQuant: Redefining AI efficiency with extreme compression

[Database] Show HN: DuckDB community extension for prefiltered HNSW using ACORN-1 Hey folks! As someone doing hybrid search daily and wishing I could have a pgvector-like experience but with actual prefiltered approximate nearest neighbours, I decided to just take a punt on implementing ACORN on a fork of the DuckDB VSS extension. I had to make some changes to (vendored) usearch that I&#x27;m thinking of submitting upstream. But this does the business. Approximate nearest neighbours with WHERE prefiltering.<p>Edit: Just to clarify, this has been accepted into the community extensions repo. So you can use it like:<p>```<p>INSTALL hnsw_acorn FROM community;<p>LOAD hnsw_acorn;<p>```

[Other] Zero-Cost POSIX Compliance: Encoding the Socket State Machine in Lean's Types

[Other] Go Naming Conventions: A Practical Guide

[Other] Show HN: AI Roundtable – Let 200 models debate your question Hey HN! After the Car Wash Test post got quite a big discussion going (400+ comments, <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=47128138">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=47128138</a>), I spent the past few weeks building a tool so anyone can run these kinds of questions and get structured results. No signup and free to use.<p>You type a question, define answer options, pick up to 50 models at a time from a pool of 200+, and they all answer independently under identical conditions. No system prompt, structured output, same setup for every model.<p>You can also run a debate round where models see each other&#x27;s reasoning and get a chance to change their minds. A reviewer model then summarizes the full transcript. All models are routed via my startup Opper. Any feedback is welcome!<p>Hope you enjoy it, and would love to hear what you think!