Vantom
Built Different

Everything local.
Nothing leaked.

Vantom’s pipeline runs entirely on your machine — market data in, structured verdict out, zero telemetry, zero round-trips to a server.

Data pipeline — 5 stages

01

Live Market Data

3 sources

Binance WebSocket · Alpaca · Finnhub — asset class auto-detected

02

Detection Engine

per-candle scan

Scans every candle for FVGs, Sweeps, and BOS in real time

03

Confluence Scorer

signal stacking

Signals that cluster in the same zone stack their scores

04

AI Gate

threshold

Only setups above the confidence threshold reach the model

05

Verdict

local LLM

Structured JSON — entry, target, invalidation, thesis — on-device

Design Principles

01

Local-first by design

The reasoning model runs on your Mac. No API keys. No per-call cost. No position data transmitted anywhere. The verdict never touches a server.

02

Asset-class-aware

Crypto, equities, and forex behave differently. The detection engine uses separate parameter profiles per asset class so a BTC signal and an AAPL signal are evaluated on their own terms — not the same ruler.

03

Parallelism without blocking

Market data processing and UI updates run on the main thread. AI inference runs in an isolated background process. A slow model call never freezes a chart or drops a candle.

04

Deduplication built in

The same setup doesn't fire the AI twice. A fingerprinting layer tracks active setups and suppresses redundant calls — so you get one clean verdict per opportunity, not a flood.