Agent View
The site as an AI agent gets it, beside the site as a person sees it. What it can read, what it has to cut away, and what it never sees.
Skip to content
yippy ®
it's magic
HubsFeedB2B 26Beginner 21Consumer 16Pro 15Advanced 10Technology 48
No project
Engines
- yippy®
- Technology
- Clusty — search engine that clustered results by topic
Organization
The rest of the page is in full screen.
Organization # Clusty — search engine that clustered results by topic In the early 2000s, as the internet was rapidly expanding, a unique search engine emerged from the halls of Carnegie Mellon University. Clusty, lau... Apr 22, 2026 · updated Aug 3, 2026 · 3 min [Technology](https://yippy.com/t/y1523z53ez56scds88kf/) [Inform](https://yippy.com/t/y1kdefr9y8skczvm49by/) [Article](https://yippy.com/t/y1n9b2gj7bbphcygcmnu/) [Beginner](https://yippy.com/t/y1nmwrr82btvabv3u74d/) ## Search engine that reshaped web navigation Email Launched in 2004, **Clusty** was a groundbreaking search engine developed by [**Vivisimo**](https://yippy.com/t/y1wukf5unx6y4vmmsx5b/), a Pittsburgh-based technology company founded in 2000 by Carnegie Mellon University researchers **Raúl Valdés-Pérez**, **Jerome Pesenti**, and **Chris Palmer**. Clusty's debut signaled a new approach to Web search - one that prioritized clustering technology to tackle the overwhelming volume of information on the Web. ## The birth of Clusty Email Vivisimo recognized the need for a **more efficient way to organize and present search results**. While traditional search engines simply listed relevant web pages, Vivisimo's "clustering" technology automatically grouped these web pages into topics and subtopics. This approach led to the creation of Clusty, a user-friendly search engine that demonstrated how clustering could streamline information retrieval. Sponsored [yippy® yippy® Discover more ](https://yippy.com/) ## How Clusty worked Email Unlike typical search engines that rely on a single, linear list of results, Clusty dynamically organized content into **folder-like clusters**. As users entered queries - for example, "Walt Disney" - Clusty automatically created categories such as "**Walt Disney World**," "**Collectables**," "**History**," and "**Biography"**. This categorized view allowed users to focus on the subtopic most relevant to them, reducing the need to sift through irrelevant results. ## Features and Functionality Email Clusty offered a number of unique features that set it apart from the competition: - **Expandable folders:** Subtopic "clusters" could be expanded to reveal related topics. - **Preview windows:** Users could quickly view site snippets without leaving the Clusty interface. - **Multiple search tabs:** In addition to Web and News, Clusty offered specialized categories such as Gossip, Images, and even customizable tabs for platforms such as eBay, Slashdot, or Blogs. - **Metasearch capabilities:** Clusty pulled results from multiple search engines and aggregated them into a single results page before clustering. This innovative feature reduced search "noise" and helped users find relevant material more quickly. In addition, Clusty allowed power users-especially those interested in SEO techniques-to avoid low-quality, spam-like results. Sponsored [yippy® yippy® Discover more ](https://yippy.com/) ## Recognition and user base Email By 2010, Clusty was handling **millions of queries** each month and attracting **around 100,000 unique visitors**. Its success was due to - **Reduced search spam:** Clustering made it easier to filter out irrelevant or redundant content. - **User-friendly interface:** Clusty's folder-like categories provided a more intuitive user experience than traditional flat search results. - **Customization:** Specialized search tabs and customizable cluster settings catered to a wide range of user preferences. ## Acquisition and transition to Yippy Email In **May 2010**, **Yippy Inc.** acquired Clusty for **$5.55 million**. The deal included the **Clusty.com domain** and a license to Vivisimo's enterprise-grade **Velocity** software (later folded into **IBM Watson Explorer** after Vivisimo's own acquisition by **IBM**). Under Yippy's ownership, **Clusty** was rebranded as [**Yippy**](https://yippy.com/), aligning with the company's vision of providing a secure and private search environment. ### Clusty's Lasting Legacy Although Clusty no longer exists in its original form, its pioneering use of clustering has left an indelible mark on the search landscape: - **Search Paradigm Shift:** Clusty demonstrated the power of organizing results by topic, inspiring other platforms to explore more intuitive ways of presenting data. - **Impact on enterprise solutions:** Many of the clustering methods that began with Clusty were integrated into enterprise search technologies, shaping the development of the next generation of information retrieval tools. - **Continued Evolution:** While the Clusty name has morphed into Yippy, its core philosophy of improving the user experience through intuitive topic discovery continues to resonate in today's AI-driven search applications. By introducing clustering to everyday web queries, Clusty demonstrated how advanced algorithms could transform the user search experience, laying the groundwork for the sophisticated, personalized search tools we use today. ## Clusty Video Demonstration Email ### Author Email ET [Editorial Team](https://yippy.com/t/y12ghppvr29wcabscpmt/) ### Topics Email [Brands](https://yippy.com/t/y1xhmk6xdkthmh6ndgna/) [Profiles](https://yippy.com/t/y1gk3vsh6pkns5h79ek3/)
An agent gets this page whole: its own text is in the HTML the server sends.
The figures
1 page, set against the 168,131 sites with figures.
- Readablehigher is better
- 100%1 of 1 page
- All 168,131 sitesBetter than 47%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 77%middle page
- All 168,131 sitesBetter than 59%
Of the words before script, the share that are the page and not menus, footer and forms.
- Costshown, never scored
- 1,335tokens
- About 1,335 a page
To read every page once. A long page that answers well is not worse for it. Tokens are estimated at about 4 characters each.
How its pages spread on Clean
1 page measured.
Against its rivals
The sites nearest it by what they do, with figures. Close means similar work, not better.
| Readinghigher is better | Costnot scored | ||
|---|---|---|---|
| Site | Readable | Clean | Tokens a page |
| clusty.comThis site, 1 page | 100% | 77% | 1,335 |
| vespa.ai100 pages | 100% | 56% | 1,661 |
| seobythesea.com100 pages | 100% | 73% | 4,269 |
First of 3 on Readable, first on Clean.
AI crawler access
What robots.txt says to each, as read on October 24, 2026. 8 of 8 may read the site.
| Crawler | robots.txt says | Used for | The line that decides |
|---|---|---|---|
| GPTBotOpenAI | Not named | Training models | Falls to User-agent: * |
| OAI-SearchBotOpenAI | Not named | ChatGPT search | Falls to User-agent: * |
| ChatGPT-UserOpenAI | Not named | A page a person asks about | Falls to User-agent: * |
| ClaudeBotAnthropic | Not named | Training models | Falls to User-agent: * |
| Claude-SearchBotAnthropic | Not named | Claude’s search | Falls to User-agent: * |
| PerplexityBotPerplexity | Not named | Perplexity search | Falls to User-agent: * |
| Google-ExtendedGoogle | Not named | Training Gemini | Falls to User-agent: * |
| bingbotMicrosoft | Not named | Bing and Copilot | Falls to User-agent: * |
Every AI crawler mttr checks may read it. Not named means the rules for every crawler apply.
Every page
Worst first. Each opens in Agent View at the top.
No page loses anything an agent needs.Open the action plan
| What an agent getshigher is better | Signals | Costnot scored | ||||
|---|---|---|---|---|---|---|
| Page | Words | Clean | Readable | Main heading | Tokens | What it loses |
| /t/y1yvger5bw8yrnqr7fwz | 654 | 77% | Yes | Yes | 1,335 | Nothing |
Show where it stands
A card, a badge and a line, each with the figures.
A badge for the site
<a href="https://mttr.si/agent-view/clusty.com"><img src="https://mttr.si/agent-view/clusty.com/badge.svg" alt="Agent View: 100% readable, 77% clean" height="20"></a>
The figures in one line
clusty.com in Agent View: 100% of pages readable, better than 47% of sites; 77% clean; 1,335 tokens to read all 1 page. mttr.si/agent-view/clusty.com
What to do next
Fix the pages, let an agent do it, and read the site again to see the figures move.
Fix what agents miss
No page loses anything an agent needs. The action plan has the site’s other fixes.
Open the action planConnect your agent
Claude Code, Codex or Cursor reads the site’s fixes over MCP, fixes a page in your code, has mttr read it again, and checks the fix landed.
https://mttr.si/mcpSet up an agent
Claim the site
Prove it is yours with a DNS record or a file. Your agent can then reach its reads and jobs, and set each change to wait for your approval.
Claim the siteDrawn from the HTML mttr fetched on its read of October 24, 2026, not a screenshot, and only from the 1 page read. An assistant’s own reader may differ. Tokens are estimated at about 4 characters each. A site an agent reads well is not a site an assistant cites.