Web Speed
A shared web-map registry for AI agents (MCP, open source)
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Hey everyone, I've been working on a tool called Web Speed. It takes web pages full of HTML and parses them into an easily readable sitemap for an AI agent. By ensuring the AI doesn't have to analyze the full HTML from the page or screenshots of the page, it makes the agent a lot cheaper and faster. It's MCP-native, so any AI that supports MCP can run it and take control of your browser for you. There are both “normal” and post-auth versions live on GitHub. What I think is the coolest thing about the project is the global cache of sitemaps. When a user visits a site, it takes the sitemap and sends it up to the server so that later, a person can get that sitemap from the cache, further speeding up the agent. Right now, only the paid API version can access the cache. I would love your thoughts on the project, any ideas, criticisms, or concerns. I really just want to see if people think that this would be a useful tool. Please reach out if you have any questions about Web Speed. Repo (OSS): https://github.com/Dominic-Pi-Sunyer/web-speed-oss Repo (Post-auth): https://github.com/Dominic-Pi-Sunyer API and Docs: https://getwebspeed.ioThanks, Dominic
HN · launched Jun 8, 2026 · 7 upvotes (top 58%) · 0 views
Niche: model context protocol tools · 465 launches, 13 in the last 7 days ▼ -24% · Explore this niche →
Category and tags
- Horizontal
- Data infrastructure
- Developer
- AI-native
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 465 launches in model context protocol tools →
Could you build this?
Yes It is an open-source MCP server and HTML parser that converts web page structures into clean sitemaps for LLMs, which is easily implemented with standard libraries like Cheerio/BeautifulSoup and the Model Context Protocol SDK.
Discussion
4 comments analyzed.
Concerns raised: Large companies will build similar versions internally to reduce API costs, Not suitable for large-scale queries, better for small use cases
Feature requests: Human-readable fast-load version with just content extracted, Support for extracting raw text from full rendering pipeline (HTML/CSS/JS/JSX)
Competitors
Other products that read as similar to this one : 381 launches clear the similarity bar, closest 8 shown.
Attention rank: #220 of 382 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 217 days after the earliest competitor.
- Tabstack · hn · 2026-01-14 · 130 upvotes · similarity 0.53
- Mwe-MCP · hn · 2026-07-23 · 5 upvotes · similarity 0.52
- Rtrvr.ai · hn · 2025-11-12 · 6 upvotes · similarity 0.50
- PageAgent, A GUI agent that lives inside your web app · hn · 2026-03-05 · 147 upvotes · similarity 0.49
- browse · github · 2026-10-27 · 13 upvotes · similarity 0.48
- flick-computer-use · github · 2026-09-24 · 22 upvotes · similarity 0.46
- Browser4 · hn · 2025-12-13 · 7 upvotes · similarity 0.46
- The fastest browser for AI agents to run browser automation · hn · 2026-10-22 · 10 upvotes · similarity 0.45
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.