Hacker News

I read Cloudflare's "Markdown for Agents" article and thought this would be really powerful if it could support internal websites, JSON content and dynamic Javascript sites.

I built this on my 35-minute BART ride to SF using my phone as the IDE (and a couple of hours of feature creep/testing). It's a combination MCP server + HTTP proxy that converts web content to markdown on-the-fly.

Key features:

* HTTP/HTTPS proxy with automatic HTML to markdown conversion * Token counting and caching to stay efficient * Content negotiation (only converts when Accept: text/markdown) * MCP server * JavaScript rendering for dynamic sites

Let me know what you think!

Comments URL: https://news.ycombinator.com/item?id=47134859

Points: 1

# Comments: 0

Article URL: https://wordpress.org/plugins/masterai-rankwriter/

Comments URL: https://news.ycombinator.com/item?id=47134851

Points: 1

# Comments: 1

I've been using DigitalOcean's App Platform as an alternative. As other mentoned, it's not exactly identical, but it's really close with the git-base deployments and etc. Anyone else can share their thoughts too.

Comments URL: https://news.ycombinator.com/item?id=47134831

Points: 1

# Comments: 0

Article URL: https://developer.spotify.com/blog/2026-02-06-update-on-developer-access-and-platform-security

Comments URL: https://news.ycombinator.com/item?id=47134830

Points: 1

# Comments: 1

Article URL: https://www.aihero.dev/skill-test-driven-development-claude-code

Comments URL: https://news.ycombinator.com/item?id=47134817

Points: 1

# Comments: 0

Article URL: https://www.robinsloan.com/lab/worst-or-best/

Comments URL: https://news.ycombinator.com/item?id=47134812

Points: 1

# Comments: 0

Article URL: https://mzaks.medium.com/when-magic-becomes-explicit-mojos-take-on-metaprogramming-61bcfafc5145

Comments URL: https://news.ycombinator.com/item?id=47134785

Points: 2

# Comments: 0

Cloud PBX for small business

Comments URL: https://news.ycombinator.com/item?id=47134782

Points: 1

# Comments: 0

Article URL: https://github.com/FirebirdSQL/decimal-java

Comments URL: https://news.ycombinator.com/item?id=47134779

Points: 3

# Comments: 0

Article URL: https://pinhead.ink/

Comments URL: https://news.ycombinator.com/item?id=47134761

Points: 1

# Comments: 0

Article URL: https://www.cnx-software.com/2026/02/24/gyroidos-virtualization-solution-aims-to-secure-embedded-devices-ease-cybersecurity-certification/

Comments URL: https://news.ycombinator.com/item?id=47134732

Points: 1

# Comments: 1

Article URL: https://www.openlegion.ai/

Comments URL: https://news.ycombinator.com/item?id=47134730

Points: 4

# Comments: 3

Article URL: https://github.com/renovatebot/renovate/discussions/41414

Comments URL: https://news.ycombinator.com/item?id=47134727

Points: 1

# Comments: 0

Article URL: https://teotti.com/llm-and-mcp-a-primer/

Comments URL: https://news.ycombinator.com/item?id=47134713

Points: 1

# Comments: 1

Article URL: https://growingswe.com/blog/quadtrees

Comments URL: https://news.ycombinator.com/item?id=47134702

Points: 3

# Comments: 0

Hey HN. I've spent 10 years doing IT work, mostly infrastructure and scripting, the stuff nobody writes blog posts about. No CS degree. This is my first startup and I have no idea if I'm doing it right. Here's the problem that bugged me: every AI agent setup I looked at just blasts everything through GPT-4 or whatever the biggest model is. That's insane for 80% of tasks. You don't need a $0.03/1k token model to parse a CSV. So I built two things. Rhelm is a web app for organizing AI work visually, boards and tasks, kind of like Linear but for agent workflows. goClaw is a companion mobile app (coming to App Store and Play Store) that lets you talk to your agents from your phone. Text or voice. "Hey, spin up the data cleaning job" and it figures out which model to route it to based on what the task actually needs. The routing is the part I care about most. Task comes in, system looks at complexity, picks the cheapest model that can handle it. Sometimes that's a local model, sometimes it's an API call, sometimes it's "this actually needs a human." I built the core loop in about 4 days. I've been breaking and fixing it since. I'm not going to pretend I have everything figured out. I definitely don't. But I'm mass rounding off the rough edges and I'd rather ship something and learn from people smarter than me than sit on it forever. https://rhelm.io (waitlist is open) What am I missing? What would make you actually use something like this?

Comments URL: https://news.ycombinator.com/item?id=47134694

Points: 1

# Comments: 0

Article URL: https://en.wikipedia.org/wiki/Be_My_Baby

Comments URL: https://news.ycombinator.com/item?id=47134678

Points: 1

# Comments: 1

Built this as an experiment in giving LLMs embodied musical experience. It's an MCP server with 120 MIDI songs across 12 genres. Each genre has one fully annotated exemplar the model studies first. The rest are raw MIDI waiting to be learned.

The model can read sheet music, play songs through your speakers, view an SVG piano roll it can read back to verify what it played, and write to a practice journal that persists across sessions. Learning compounds over time.

Comments URL: https://news.ycombinator.com/item?id=47134676

Points: 1

# Comments: 0

Article URL: https://www.wsj.com/finance/currencies/binance-iran-sanctions-financing-staff-b1648133

Comments URL: https://news.ycombinator.com/item?id=47134396

Points: 1

# Comments: 0

Article URL: https://yomisensei.net/blog/bl-gl-analysis

Comments URL: https://news.ycombinator.com/item?id=47134387

Points: 1

# Comments: 0