PRIVATE BETA Full Intelligence Platform · 17 Analysis Views

The AI-native crawler that sees what search bots see

AI Spider audits your site the way AI models crawl it: extractability, citability, JS dependency, chunk quality, and retrieval readiness. Redirect intelligence, canonical analysis, PageRank, near-duplicate detection, and on-demand AI analysis for N-Grams, Citation Readiness, Section Strength, and Authority. Not just rankings. Actual AI discoverability.

Screaming Frog parity AI Retrievability Scoring Page Intelligence Panel Architecture Intelligence No LLM API key required
COMPLETE - 94 URLs · 36s · Avg Score 83
AddressStatusAI ScoreWordsResponseIssuesDepth
akshaydahiya.site 200 90 1,24441ms50
/services 200 84 1,06244ms71
/expertise/cloud-devops 200 90 1,5372.1s92
/contact 200 85 756802ms81
+90 more URLs…
13k+URLs crawled and fully paginated in a single audit
70Data columns exported to CSV
25+Issue types detected automatically
17Intelligence views across the platform

Not just a crawler. A full intelligence platform.

AI Spider goes beyond status codes and titles. It evaluates every page the way an AI language model would encounter it - and scores it accordingly.

AI Retrievability Score

Six-dimensional scoring per page: extractability, citability, structure, AI crawlability, chunk quality, and link authority. Aggregated into a single 0-100 score.

Full Resource Discovery

Crawls HTML pages AND discovers images, JavaScript, CSS, PDFs, and fonts via HEAD requests. Full site inventory like Screaming Frog - not just HTML.

Real-Time SSE Updates

Watch pages appear in the URL table live during crawl. Scores, signals, and issue counts update the moment each page is processed.

Server-Sent Events

Redirect Intelligence

Detects redirect chains (3+ hops), redirect loops, mixed 301/302 chains, and redirects pointing to noindex pages. Full chain visualisation.

Canonical Intelligence

Canonical chains, loops, canonical pointing to 404/noindex/redirect pages. Goes beyond "has a canonical" to verify the canonical is actually valid.

Architecture Reporting

Directory-level aggregations: avg AI score per folder, avg crawl depth, issue rate, page count. Understand your site structure at a glance.

PageRank + HITS Authority

Internal PageRank via power iteration plus HITS hub and authority scores. Orphan detection, buried authority pages, leakage analysis, and dead-end flagging.

HITS Algorithm

Near-Duplicate Detection

MinHash Jaccard similarity across all pages post-crawl. Exact duplicates via SHA-256 hash, near-duplicates at 80%+ content overlap. Fully algorithmic. No LLM required..

MinHash · 128 hash functions

Actionable Recommendations

22+ site-wide and per-page recommendations backed by real data - structured data gaps, AI crawler blocks, citation readiness, section strength, authority leakage, and more.

/pages/recommendations

Page Intelligence Panel

Click any URL in any tab to open a full-detail drawer: AI scores, bot access, content signals, inlinks/outlinks with anchor analysis, and per-page fixes.

Universal page drawer

Citation Readiness

Scores every page on how citable it is - statistics, dates, source attributions, quotes, tables, and lists. Identifies pages AI systems are likely to cite vs ignore.

Post-crawl analysis

Section Strength Analysis

Scores each content section (H2 block) on word count, lists, tables, numbers, and links. Identifies weak sections that undermine AI extractability.

Per-section scoring

N-Gram Phrase Intelligence

Extracts the most frequent 2- and 3-word phrases across all crawled content. Reveals your site's key topics and terminology as AI systems actually see them.

Post-crawl NLP

Resource Explorer

Full inventory of JS, CSS, images, fonts, and media. MIME-type aware classification, broken resource detection, and found-on-page counts.

MIME-aware

Architecture Intelligence

Directory tree with avg AI score, issue rate, and depth per folder. Orphan pages, weakly-linked pages, buried authority detection, excessive outlinks, and dead-end page analysis.

4 sub-views

Everything runs automatically after the crawl

Core analysis runs automatically after every crawl. On-demand tabs (N-Grams, Citation, Section Strength, Authority) run on the URLs you select, so you stay in control of what gets analysed.

  • Redirect Chain + Loop Analysis

    Walks every redirect chain, flags loops and long chains with full hop visualisation

  • Canonical Intelligence

    Validates every canonical tag destination - not just presence

  • Near-Duplicate Detection

    MinHash Jaccard similarity across all page text. Exact + near-exact duplicates

  • Internal PageRank + HITS

    Power-iteration PageRank and HITS hub/authority scores on the internal link graph

  • N-Gram Phrase Intelligence on-demand

    Extracts 2- and 3-word phrases from selected pages to reveal key topics as AI systems see them.

  • Citation Readiness on-demand

    Deterministic scan for statistics, dates, sources, quotes, tables, and lists. Run on selected URLs from the Citation tab.

  • Authority / HITS on-demand

    Hub and authority scores via the HITS algorithm on selected pages. Identifies buried authority, dead ends, and leaking pages.

  • Section Strength on-demand

    Per-chunk scoring of word count, structure, and data richness for every H2 section. Run on selected URLs.

Post-Crawl Summary - akshaydahiya.site Complete
Pages Crawled94
Resource URLs269
Avg AI Score83
Avg Citation Score71
Avg Section Strength48
Avg Authority Score62
Redirect Chains3
Redirect Loops0
Canonical Issues7
Orphan Pages4
Near Duplicates2
AI Bots Blocked0
JS-Dependent Pages4
Total Issues105

22+ issue types across 11 categories

Every issue is categorised by severity and linked to the affected page. Issues feed the recommendations engine directly.

GPTBot / ClaudeBot / PerplexityBot blocked
JS-dependent content (AI can't read)
Redirect loop detected
Canonical points to 404 page
Missing H1 tag
Very thin content (<100 words)
Long redirect chain (3+ hops)
Canonical chain (A→B→C)
High boilerplate ratio (>85%)
No author signal detected
Missing meta description
Exact duplicate content
Orphan page - 0 internal inlinks
Content difficult to read (Flesch <40)
Missing structured data (Schema.org)
Images missing alt text
llms.txt not present
Buried authority page (deep + high PR)
hreflang missing return tags
Page missing from XML sitemap
URL contains uppercase characters
Near-duplicate content detected

Production-grade. Local-first.

Built on a modern full-stack architecture. Runs entirely on your machine - no cloud, no data leaving your infrastructure.

Frontend

  • Vite 7 + React 19 + TypeScript 5.9
  • React Router v7 (file-based routing)
  • Tailwind CSS v4 + CSS variables
  • react-window virtualised URL table
  • Recharts for visualisations

Backend

  • Node.js + Express REST API
  • SQLite via better-sqlite3 (session DB)
  • Raw SQL migrations (fresh per session)
  • Server-Sent Events for live updates
  • Axios with retry + redirect capture

Processing - Zero LLM Dependency

  • No API key required - fully algorithmic
  • MinHash Jaccard (duplicate detection)
  • HITS power iteration (authority)
  • Flesch-Kincaid readability scoring

Data + Export

  • 70-column CSV export
  • HTML report + Markdown ZIP + llms.txt export
  • Session-based DB per crawl
  • Sitemap generation
COMING SOON

LLM-powered analysis for deep retrieval intelligence

The next frontier of AI Spider. These features go beyond deterministic signals - using large language models to understand how AI systems reason about, retrieve, and reconstruct your content.

Content Intelligence
  • Information Gain Identifies the unique insights your content contributes compared to competing pages - original facts, claims, and perspectives that add value beyond commonly repeated information.
  • Coverage Score Measures how comprehensively a page addresses a topic - whether important subtopics, entities, questions, and supporting information are present for a complete answer experience.
  • Coverage vs Confidence Balances breadth of coverage with how trustworthy and well-supported the information appears - evidence quality, authority signals, and supporting claims.
Entity & Knowledge Analysis
  • Entity Expansion Discovers related entities, concepts, brands, products, and topics connected to your content - uncovering opportunities to strengthen topical authority across a website.
  • Multi-Hop Relationship Analysis Maps connections between entities, concepts, and facts across content - identifying how information links together and revealing opportunities to strengthen topical depth.
  • Retrieval Drift Analysis Tracks how information evolves as retrieval systems gather and expand knowledge around a topic - identifying gaps between original query intent and information ultimately surfaced.
Query & Retrieval Intelligence
  • Query Expansion Intelligence Reveals related searches, synonyms, concepts, and topic variations associated with a target query - identifying content opportunities across a wider range of user intents.
  • Retrieval Compression Analyses how effectively a page can be distilled into key facts, claims, and evidence. Highlights content that is easy for modern AI systems to process and reference.
  • Complex Query Reformulation Breaks down sophisticated user questions into underlying concepts, entities, and information needs - identifying the content required to answer complex searches more effectively.

AI Spider vs Screaming Frog

Screaming Frog is the gold standard for technical SEO crawling. AI Spider matches it on the fundamentals and goes further on AI-specific signals.

FeatureScreaming FrogAI Spider
HTML page crawling
Resource URL discovery (images, JS, CSS)
AI Retrievability Scoring
GPTBot / ClaudeBot access analysis
Content chunking for AI retrieval
Citation Readiness scoring
Section Strength analysis
HITS hub + authority propagation
N-Gram phrase intelligence
llms.txt detection
Near-duplicate detection (MinHash)
22+ recommendation engine
Redirect chain detection
Canonical intelligence
Internal PageRank
Structured data extraction
Real-time crawl updates✓ (SSE live)
Architecture Intelligence (4 sub-views)
Page Intelligence Panel
Internal Link Explorer
Resource Explorer (MIME-aware)
MCP server integration✓ (v24)Planned
Runs locally (no cloud)✓ (desktop app)✓ (local server)
Pricing€245/yearFree during beta

Start auditing AI retrievability today

No LLM API key required. Runs locally. Free during private beta.

View on GitHub →