v1 API now available

The Business Data Layer
for AI Agents

Give your AI agents structured, confidence-scored business data — via REST API or MCP. One call returns a complete Agent Business Object (ABO) with identity, offerings, trust signals, and 40+ normalized fields.

~200ms cached500 free creditsREST + MCP
Get API Key

Claim 500 credits for free. No credit card needed.

Explore
02 · The problem

The web was built for humans.
Not agents.

What agents see today

Unstructured pages, buried facts, and layout noise — not a reliable business record.

HTMLScriptsNavigationVisual clutter
What Vexi compiles

Structured Agent Business Objects optimized for machine retrieval — one format, every business.

Raw Websites
Vexi ABO
Inconsistency
Every site uses a different layout. Custom parsers break when markup changes.
One schema. Every business. Each object follows the same canonical structure — write retrieval logic once.
Reliability
Extracted fields drift. Contact details go stale. Failures surface only in production.
Quality metadata on every object. completeness_score, confidence, and missing_fields make gaps explicit.
Cost
HTML-heavy responses burn tokens. Each lookup repeats extraction and verification.
Retrieval-first delivery. Cached objects return in ~200ms. Repeat access avoids re-parsing the web.

The business web, compiled for agent retrieval.

03 · How it works

From websites to structured
business intelligence.

01

Crawl

Vexi crawls public business websites and extracts meaningful business information.

search_businesses({
  query: "CRM for startups",
  location: "Brazil"
})
02

Normalize

Raw content is normalized into an Agent Business Object (ABO) — a standardized business schema optimized for machine retrieval.

← cache hit: 187ms
← crawling: ~30s
03

Retrieve

Agents access structured business intelligence through API and MCP-native retrieval.

actions[0].url  "https://cal.com/sales"

Easy to set up. Easy to maintain.

No pipelinesNo schema upkeepNo parser maintenance
04 · API

Business intelligence through a single
unified API.

Developers integrate Vexi once and gain access to structured business intelligence normalized for AI systems.

Intelligent searchLive crawlABO schema
request.shGET
curl -X GET "https://api.getvexi.dev/v1/search" \
  -H "Authorization: Bearer $VEXI_KEY" \
  -d '{
    "query": "scheduling software",
    "location": "San Francisco",
    "limit": 1
  }'
response.json 187 ms · cache hit
{
  "results": [{
    "name": "Cal.com",
    "business_type": "saas",
    "description_short": "Open-source scheduling infrastructure for everyone.",
    "offerings": {
      "services": [
        { "name": "Team Scheduling", "category": "Scheduling" },
        { "name": "Enterprise SSO",  "category": "Security"   }
      ],
      "pricing": {
        "model": "freemium",
        "starting_from": "$12/month",
        "free_tier": true
      }
    },
    "contact": {
      "website":  "https://cal.com",
      "email":    "support@cal.com",
      "linkedin": "https://linkedin.com/company/calcom"
    },
    "trust": {
      "differentiators": [
        "Open source with 30k+ GitHub stars",
        "Self-hostable — full data control"
      ],
      "ratings": [{ "platform": "G2", "score": "4.7/5" }]
    },
    "agent_interface": {
      "actions": [
        { "name": "Book a demo",     "url": "https://cal.com/sales",        "method": "link" },
        { "name": "Start free trial", "url": "https://app.cal.com/signup",   "method": "link" }
      ],
      "intents_matched": [
        "schedule a meeting", "book a demo", "find scheduling software"
      ],
      "tags": ["scheduling", "open-source", "saas"]
    },
    "quality": {
      "completeness_score": 94,
      "confidence":         "high",
      "data_freshness":     "fresh"
    }
  }],
  "total_ready": 1,
  "source": "intelligent_search",
  "meta": { "wait_time_ms": 187 }
}

Truncated ABO response. Full Agent Business Object includes 40+ normalized fields across 8 sections.

Want to see the full ABO?Go to Playground
05 · Infrastructure

Built for agent-native retrieval.

Schema, access, and quality signals in one layer — so agents retrieve business facts, not HTML.

Unified semantic schema

Every business is returned as an ABO — a standardized schema your agents can rely on, every time.

MCP-native access

Agents can access the Vexi network as native tools through MCP-compatible frameworks.

Demand-driven expansion

New agent queries automatically expand the network through real-time crawling and normalization.

Optimized for agent retrieval

Structured business objects reduce parsing overhead and improve agent reliability.

Confidence-scored outputs

Every business object includes quality and confidence signals so agents can reason on reliable data instead of raw extraction.

Agent Business Objects (ABOs)

One consistent object format across SaaS, local businesses, marketplaces, and global enterprises.

Works with every major agent framework.

REST API or native MCP — your choice.

v1 · Production

Compiling the business web
for AI agents.

Structured business intelligence for autonomous systems and developer platforms.

500 credits freeNo credit cardv1 production API
Get API Key →