github·Trading and markets
Solari Sentinel: Microsecond Crypto Risk Gate
A sub-15ms risk checking layer sitting between automated trading algorithms and order book execution to abort rogue orders.
Open GitHub (solari-labs) ⚡ ~14 ms · 0.01% false positive
Solari Labs
@solarilabs
Hardware latency matters in market making. Jev provides calibrated probability thresholds before any capital is committed.
Is this trading execution within calibrated portfolio drawdown boundaries?
Jev sits between the incoming context and the next system action. Rather than generating lengthy, slow natural language that requires brittle regex parsing, Jev returns non-autoregressive, calibrated probabilities that downstream code can immediately execute.
01allow_executionPrimary action
02risk_scoreConfidence score
03max_slippageFallback route
Related Trading and markets Builds
xpost
Inspectjev-trader
I built a trading bot with Jev! Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades. It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block. Demo link → jev-trader.vercel.app