Wickra GenomeThe market as vectors.

The query is JSON, not code ​

A GenomeSpec is a list of features, a symbols universe, a normalize mode and a metric. Build the vectors once, then query by similar, cluster or anomaly — all over the JSON command protocol.

{
  "features": [
    { "kind": "indicator", "name": "Rsi", "params": [14] },
    { "kind": "indicator", "name": "Atr", "params": [14] },
    { "kind": "price", "field": "close" }
  ],
  "symbols": ["BTCUSDT", "ETHUSDT", "SOLUSDT"],
  "normalize": "z_score",
  "metric": "cosine",
  "seed": 24333
}

Install ​

The same vector database from every language — native Rust, Python, Node.js and WASM, plus a C ABI for C, C++, C#, Go, Java and R.

pip install wickra-genome

Query it from any language ​

Construct a Genome from the JSON spec, build the vectors, then similar, cluster or anomaly. Every binding returns the same results.

import json
from wickra_genome import Genome

spec = json.dumps({
    "features": [{"kind": "price", "field": "close"}],
    "symbols": ["AAA", "BBB", "CCC"],
    "normalize": "z_score", "metric": "euclid", "seed": 24333,
})

g = Genome(spec)
data = {
    "AAA": [{"time": 0, "open": 1, "high": 1, "low": 1, "close": 1, "volume": 0}],
    "BBB": [{"time": 0, "open": 2, "high": 2, "low": 2, "close": 2, "volume": 0}],
    "CCC": [{"time": 0, "open": 100, "high": 100, "low": 100, "close": 100, "volume": 0}],
}
g.command(json.dumps({"cmd": "build", "data": data}))
neighbours = json.loads(g.command(json.dumps({"cmd": "similar", "symbol": "AAA", "k": 2})))
print(neighbours)

Built on the Wickra core ​

Wickra Genome is part of the Wickra ecosystem. It builds each asset's vector from the 514 indicators of wickra-core — the same numbers a backtest or a live chart sees, turned into a searchable geometry of the whole market.

Wickra Genome is a software library, not a trading system, and comes with no warranty — use at your own risk.