be084b5154
Multi-strat with foxhunt's own ideas. (1) Combine uncorrelated premia: ~0.72 Sharpe 2019-26 but ~=60/40, only when streams net-positive (traditional 2010-26 combine +0.51 < equity +0.68 = dilution). (2) Edge-decay-trust allocation (Page-Hinkley theta, resurrection) genuinely helps: +0.16->+0.27, correctly down-weights decayed streams. (3) Static risk layer crushed returns (one-way latch); ADAPTIVE layer (continuous self-recovering DD de-lever + Kelly-floor + z-score corr + EMA vol) beat it (+0.03->+0.14, maxDD -18.7->-14.5) -- value is drawdown control. (4) THE MOAT = cheap financing: adaptive 1x Sharpe +0.48 vs 2x +0.14; retail 6-7% margin kills leverage benefit. Funds lever ~0.7 Sharpe only via prime-brokerage SOFR+1-2%. Deployable best = ~1x adaptive-risk-managed diversified book (~0.5-0.7 Sharpe, unlevered), scales with capital. Foxhunt ideas improve execution (validated); engine value = risk-mgmt not alpha. Ceiling ~0.7 ironclad. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Foxhunt
Production HFT trading system in Rust.
Architecture
The workspace contains 32 crates organized as follows:
Core Libraries (16)
| Crate | Purpose |
|---|---|
trading_engine |
Order processing, FIX 4.4, IB TWS, SIMD, RDTSC timing |
risk |
VaR, Kelly, circuit breakers, kill switches, compliance |
risk-data |
Risk data types and shared structures |
trading-data |
Trading data types |
ml |
DQN Rainbow, PPO, TFT, Mamba2, ensemble inference |
ml-data |
ML data types and feature definitions |
data |
Market data ingestion and storage |
backtesting |
Replay engine, strategy tester |
adaptive-strategy |
Ensemble execution, microstructure analysis |
common |
Shared types, resilience, error handling |
storage |
S3 and local model storage |
model_loader |
Model serialization and loading |
market-data |
Market data feed handlers |
database |
PostgreSQL access layer (SQLx) |
config |
Configuration management |
tli |
CLI commands and tooling |
Services (8)
| Service | Purpose |
|---|---|
backtesting_service |
gRPC backtesting service |
broker_gateway_service |
FIX routing, broker connectivity |
trading_service |
Core trading operations |
ml_training_service |
Model training orchestration |
data_acquisition_service |
Market data acquisition |
trading_agent_service |
Autonomous trading agents |
api_gateway |
gRPC API gateway with auth |
web-gateway |
Axum REST + WebSocket gateway |
Frontend
web-dashboard/ -- React 19 + TypeScript + Vite + TradingView charts.
Building
# Check compilation (no PostgreSQL required)
SQLX_OFFLINE=true cargo check --workspace
# Run tests for a specific crate
SQLX_OFFLINE=true cargo test -p <crate> --lib
# Clippy
SQLX_OFFLINE=true cargo clippy --workspace
ML Models
Four production model architectures on Candle v0.9.1 with CUDA:
- DQN Rainbow -- Deep Q-Network with prioritized replay, dueling heads, noisy nets
- PPO -- Proximal Policy Optimization with GAE and LSTM policies
- TFT -- Temporal Fusion Transformer for multi-horizon forecasting
- Mamba2 -- State space model for sequence prediction
Each model has a standalone trainer and a UnifiedTrainable adapter for the hyperopt pipeline.
Infrastructure
- Git: Gitea at
git.fxhnt.ai(Tailscale-only), Scaleway DEV1-S - Observability: OpenTelemetry OTLP (env
OTEL_EXPORTER_OTLP_ENDPOINT) - Database: PostgreSQL with SQLx offline mode for CI
License
Proprietary. All rights reserved.