24 million chart patterns, one API call

Request

curl "https://chartlibrary.io/api/v1/market-context"

Response

{
  "SPY": {"close": 679.46, "change_pct": -0.07, "volume": 42305622},
  "QQQ": {"close": 611.07, "change_pct": 0.14, "volume": 33605274},
  "IWM": {"close": 261.30, "change_pct": -0.25},
  "volatility": {"realized_20d_annualized_pct": 14.2, "percentile_252d": 0.48, "label": "normal"},
  "regime": {
    "label": "bull+volatile",
    "cluster": 1,
    "volatility": "elevated",
    "trend": "rising"
  },
  "sectors": {
    "spy_5d_return": -2.14,
    "leaders":  [{"symbol": "XLE", "return_5d": 2.1}],
    "laggards": [{"symbol": "XLK", "return_5d": -3.2}]
  },
  "signal_crowding": {"bullish": 4, "bearish": 8, "neutral": 8}
}

Then analyze with regime-aware matching

curl -X POST "https://chartlibrary.io/api/v1/analyze" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "NVDA",
    "context_weight": 0.05,
    "same_sector": true,
    "format": "agent"
  }'

context_weight weights matches that happened in similar regimes. same_sector restricts matches to the query's own GICS sector (peer-relative). format=agent strips visualization data to cut token usage ~80%.

Python

import requests

# One call — full intelligence for any symbol
r = requests.get(
    "https://chartlibrary.io/api/v1/intelligence/NVDA",
    headers={"Authorization": "Bearer cl_your_key"},
    params={"compact": True}
)
data = r.json()

print(f"Top match: {data['matches'][0]['symbol']} {data['matches'][0]['date']}")
print(f"10-day outlook: {data['follow_through']['horizon_returns']['10']['mean']:+.1f}%")
print(f"Regime: {data['regime']['spy_summary'][:100]}...")

JavaScript

const res = await fetch(
  "https://chartlibrary.io/api/v1/intelligence/NVDA?compact=true",
  { headers: { Authorization: "Bearer cl_your_key" } }
);
const { matches, follow_through, regime, summary } = await res.json();