Accept-md – One command to make Next.js sites LLM-scraping friendly
I recently saw a post from the Vercel CEO pointing out that LLMs understand websites much better when they can request: `Accept: text/markdown` Most websites today are built for humans. When AI agents try to consume them, they get complex HTML instead of clean, structured content. So I built *accept-md* – a simple open-source package for Next.js that helps solve this. Getting started is intentionally minimal: ``` npx accept-md init ``` After that, your existing Next.js routes can automatically respond with Markdown whenever an AI agent (or any client) requests it. No redesigns, no CMS…
What it does
In the maker’s words, at launch
I recently saw a post from the Vercel CEO pointing out that LLMs understand websites much better when they can request: `Accept: text/markdown` Most websites today are built for humans. When AI agents try to consume them, they get complex HTML instead of clean, structured content. So I built *accept-md* – a simple open-source package for Next.js that helps solve this. Getting started is intentionally minimal: ``` npx accept-md init ``` After that, your existing Next.js routes can automatically respond with Markdown whenever an AI agent (or any client) requests it. No redesigns, no CMS changes, and no duplicate pages to maintain. Right now the project is: * Focused only on Next.js * Middleware-based and lightweight * Designed to work with existing apps * A small step toward more AI-friendly websites This is an early experiment, but I think the idea itself matters as AI agents become first-class consumers of the web. I’ve open-sourced it and would love help with: * Better markdown extraction * Edge cases across Next.js setups * Performance and caching * Tests and examples * Documentation * Eventually adapters for other frameworks Would love feedback from the HN community on the approach – and whether `Accept: text/markdown` feels like a pattern worth standardizing for the AI-native web.
Does the same job
all alternatives →- WWWhy write code if the LLM can just do the thing? (web app experiment)Nov 2025 · github.com · ▲436
I spent a few hours last weekend testing whether AI can replace code by executing directly. Built a contact manager where every HTTP request goes to an LLM with three tools: database (SQLite), webResponse (HTML/JSON/JS), and updateMemory (feedback). No routes, no controllers, no business logic. The AI designs schemas on first request, generates UIs from paths alone, and evolves based on natural language feedback. It works—forms submit, data persists, APIs return JSON—but it's catastrophically slow (30-60s per request), absurdly expensive ($0.05/request), and has zero UI…
Geekflare Scraping API v2Apr 2026 · geekflare.com · ▲84RAG-ready web scraping that cuts your LLM token costs
- IWI wrote an open-source browser alternative for Computer Use for any LLM2024 · github.com · ▲180
Hey HN, I made Browser-Use, an open-source tool that lets (all Langchain supported) LLMs execute tasks directly in the browser just with function calling. It allows you to build agents that interact with web elements using natural language prompts. We created a layer that simplifies website interaction for LLMs by extracting xPaths and interactive elements like buttons and input fields (and other fancy things). This enables you to design custom web automation and scraping functions without manual inspection through DevTools. Hasn't this been done a lot of times? Good question, as a general…
- CHConvert HTML DOM to semantic markdown for use in LLMs2024 · github.com · ▲146
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
