Live — 13 sources crawled in parallel

Your RAG Pipeline Answered With Confidence. The Source Was 18 Months Old. Nothing broke. Nothing warned you.

Knowledge Universe scores every result for freshness, decay, and authority before it enters your pipeline. One API. 13+ official sources. Stop gluing connectors together.

500 calls/month free. No credit card. Works with LangChain, LlamaIndex, any LLM stack.

// Why developers switch

Three problems. Heard 200+ times.

3.9s
Cold query
14ms
Cache hit
13+
Sources crawled
2.52/3
Relevance score
Silent Failure

Stale data. Zero warning.

Cosine similarity 0.94 on an 18-month-old doc. Your retriever does its job perfectly. Your user gets a confidently wrong answer. No exception. No warning.

→ Decay score on every result. Stale = flagged before it enters.
8 API Integrations

GitHub + arXiv + YouTube + SO + ...

Different schemas. Different rate limits. Different error modes. You spend 6 weeks building the data layer. Your actual product waits.

→ One call. 13+ sources. One normalized schema.
No Confidence Signal

API returns results. Were they any good?

Every retrieval API (Tavily, Exa, SerpAPI) returns results confidently — even when they don't match your query. You never know until a user complains.

→ Coverage Confidence Score. Low match = warning + better queries suggested.
// Quickstart — 60 seconds to first result
curl -X POST https://vlsiddarth-knowledge-universe.hf.space/v1/discover \
  -H "X-API-Key: ku_test_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "topic": "transformer architecture",
    "difficulty": 3,
    "formats": ["pdf", "github", "stackoverflow"]
  }'
import requests

resp = requests.post(
    "https://vlsiddarth-knowledge-universe.hf.space/v1/discover",
    headers={"X-API-Key": "ku_test_your_key_here"},
    json={"topic": "transformer architecture", "difficulty": 3,
          "formats": ["pdf", "github"]}
).json()

# Every result has a decay_score
for sid, decay in resp["decay_scores"].items():
    print(f"{decay['label']:10} score={decay['decay_score']} {sid}")

# Coverage confidence — did KU find good results?
cov = resp["coverage_intelligence"]
if cov["coverage_warning"]:
    print("Low confidence. Try:", cov["suggested_queries"])
{
  "total_found": 8,
  "credits_used": 1,  "credits_remaining": 499,
  "decay_scores": {
    "arxiv:1706.03762": {
      "decay_score": 0.847, "label": "stale", "age_days": 2736
    }
  },
  "coverage_intelligence": {
    "confidence": 0.71, "confidence_label": "high",
    "coverage_warning": false,
    "suggested_queries": []
  },
  "sources": [/* normalized Source objects */]
}
// Pricing

Start free. Pay when you scale.

Free
$0/month
500 calls / month
  • 13+ knowledge sources
  • Decay scoring on every result
  • Coverage Confidence Score
  • JSON + Embeddings output
  • No credit card
Get started →
Growth
$79/month
20,000 calls / month
  • Everything in Starter
  • Batch embeddings
  • Cross-source deduplication
  • Slack support
Get started →
Pro
$199/month
75,000 calls / month
  • Everything in Growth
  • SLA guarantee
  • Dedicated support
  • On-prem option
Get started →