Independent developer working on AI development infrastructure, distributed systems, protocol design, and applied quantitative finance. My work spans long-horizon agent workflows, consensus-level infrastructure, and trading systems, with a focus on building things that are correct, verifiable, and grounded in real constraints rather than abstraction.
Selected work
mandrel(open source, Apache-2.0) — a protocol for long-horizon AI coding: task-scoped work, selective project memory, and deterministic control outside the model. → GitHub ↗ · project overview ↗ · full write-up ↗
Orch-Hub(closed-source) — a multi-repository orchestration platform for coordinating AI coding agents across concurrent worktrees, with dependency-aware workflows, approval gates, and real-time execution visibility. → project overview ↗
QuantX(closed-source) — a Go-based quantitative trading platform: systematic strategies with backtest-to-live parity and a research loop that combines human-defined priors with AI-assisted exploration. → project overview ↗
HKChain(closed-source) — a compliance-native Layer 1 for stablecoin issuance and RWA tokenization, aligned with Hong Kong's regulatory framework. Designing protocol-level compliance enforcement and governance. → project overview ↗