Agentic Quantitative Trading

Autonomous AI agents for trade intelligence, risk management, and order execution — communicating via open protocols.

Services

Spark

Agentic Trade Intelligence
  • AI-powered trade ideas via DSPy + Gemini
  • Real-time options analytics (SABR, risk reversals, term structure)
  • Portfolio recommendations with quantitative scoring
  • llms.txt + MCP discovery endpoints
spark.igniteedge.ai

Mercurius

Agentic Risk Firewall
  • 28-station sequencer risk pipeline
  • 3 margin models: RegT, Portfolio Margin, SPAN
  • Gate A (LLM semantic) + Gate B (math firewall)
  • 50+ strategy matchers, 4 option pricing models
mercurius.igniteedge.ai

OMS

Agentic Order Management
  • 5-step pipeline: Spark → Risk/Margin/Compliance → Mercurius → OMS → SOR
  • Real-time order ledger with audit trail
  • Billing and credits system
  • Multi-broker routing (Schwab, IBKR)
oms.igniteedge.ai

SPAN 2

CME Margin Engine
  • Four-component margin: HVaR + Stress + Liquidity + Concentration
  • Pod-based margining with cross-pod correlation offsets
  • Stress testing: historical SVaR, EVT, Heston, correlation breakdown
  • Model calibration against CME published margins
span2.igniteedge.ai

Platform Capabilities

llms.txt Discovery

Every service exposes /llms.txt and /llms-full.txt for AI agent discovery — a machine-readable description of available endpoints.

all services

MCP Protocol

Model Context Protocol endpoints allow AI agents to discover and invoke tools programmatically.

Spark · Mercurius · SPAN 2

x402 Micropayments

Pay-per-call API access gated by x402 protocol on Base Sepolia. No API keys — just on-chain payments.

Spark · Mercurius

Agentic Architecture

Services operate as autonomous agents — Spark generates ideas, Mercurius validates risk, OMS executes orders.

platform-wide