AEGIS
★ 371Runtime policy enforcement for AI agents — cryptographic audit trail, human-in-the-loop approvals, and a kill switch. Zero code changes to adopt.
About
I want to build powerful, human-centered LLMs — reliable enough to trust and wired to real-world resources — so that AI frees people's productivity and creativity, and makes everyday life genuinely better.
I'm an honors graduate of the University of Southern California's M.S. in Computer Engineering and a Shanghai Jiao Tong University alumnus, researching at USC's Fortis Lab, advised by Yue Zhao. My research spans agent safety, LLM reasoning, and world models — the pieces I believe a trustworthy, human-centered AI needs — and I turn each idea into a shipped, open-source system.
The through-line is reliability: an AI you can hand real resources to must verify its own actions, reason soundly, and model the world before it acts. Along the way I've built recommendation models at JD.com, low-latency trading infrastructure at Optiver, and autonomous GEO/SEO agents at Topify.AI. Outside research I'm building Serica, turning global curiosity about China into real trips.
Education
Open-Source · Flagship
Runtime policy enforcement for AI agents — cryptographic audit trail, human-in-the-loop approvals, and a kill switch. Zero code changes to adopt.
Constitution-first AI orchestration: one YAML Charter defines mission, budget & rules. CEO plans → CFO approves → Ledger tracks every cent & token → Auditor scores. 16 workers, Stripe, MCP.
Publications
2026 · first-author unless noted. Aojie Yuan highlighted. See Google Scholar for the full list & citations.
Experience
login() handling silent/explicit sign-in and all auth states.Awards & Honors
NVIDIA Academic Grant Program — AEGIS named among the funded open-source projects (USC Fortis Lab) 2026
Amazon Research Award — AI auditing & agent security; AEGIS & Sovereign-OS among the named projects (USC Fortis Lab)
Memory Genesis Competition — Public Value Award · Evermind Hackathon 2026
China Collegiate Programming Contest (CCPC) — Gold Award 2024
China Collegiate Programming Contest (CCPC) — Silver Award 2023
China International College Students' Innovation & Entrepreneurship Competition (“Internet+”) — Second Prize
Mathematical Contest in Modeling (MCM) — Honorable Mention 2023Academic Service
Reviewer — International Conference on Machine Learning (ICML) 2026
Reviewer — Conference on Empirical Methods in Natural Language Processing (EMNLP) 2026Currently Building
The runtime safety layer for AI agents — cryptographic audit trail, human-in-the-loop approvals, and a kill switch, adopted with zero code changes. 371★ open-source, live at aegistraces.com.
Charter-governed AI orchestration: a YAML constitution sets mission, budget & rules; CEO plans → CFO approves → Ledger tracks every cent & token → Auditor scores. 16 workers, Stripe, MCP. 102★ open-source.
A China-inbound travel platform that turns global curiosity about China into real, bookable trips — AI-generated itineraries, cultural adaptation, and a conversion funnel built for overseas travelers.
An AI agent that makes professional warm introductions — it reasons over your network and goals to broker curated, high-signal intros to the right people, then handles the outreach end to end.