🤓 Latest Submissions
ThetaGuard - Systematic Defined-Risk Agent
ThetaGuard is a multi-agent options trading system built for the Income & Portfolio Overlay Agents track. It systematically sells defined-risk put credit spreads on SPY and QQQ, harvesting time decay in calm markets — while a dedicated Event-Risk Agent enforces hard lockouts ahead of scheduled macro releases like JOLTS and Non-Farm Payrolls. Five agents cooperate on every cycle. The Event-Risk Agent checks the macro calendar first, before anything else runs. The Strategy Selector only proposes a trade when 52-week realized volatility rank clears a 30.0 floor, targeting a -0.15 to -0.20 delta short leg on a $5-wide spread. Expiry selection is proactive, not reactive: it only chooses expiries that mature before the next blackout window begins, so the agent never has to force-close a healthy position early. The Risk Manager caps exposure at two concurrent spreads and five percent of account equity. The Execution Agent logs full reasoning before submitting any order, and the Reporter Agent compiles a daily audit trail. The system runs against Alpaca's live paper Trading and Market Data APIs, with the Alpaca CLI driving the production execution loop and the Alpaca MCP Server used during development for conversational inspection with Claude and Antigravity.
4 Sep 2026
JobShield
JobShield is a job offer legitimacy checker for job seekers worldwide. Users paste a job posting, recruiter message, or freelance/gig offer (plus an optional company website domain) and receive an AI-powered risk analysis with a score, specific red flags, and plain-language advice. Results are saved to a personal dashboard with community stats for social proof. - Protect job seekers from employment scams by providing instant, explainable risk analysis. - Cover all channels (email, LinkedIn, WhatsApp, freelance platforms) via a simple paste-and-check interface. - Provide a persistent history dashboard so users can track and verify offers over time. - Build a feedback loop where users mark outcomes (confirmed scam / confirmed legitimate) to contribute to community stats.
10 Aug 2026
Mini-Jarvis Onboarder
Every new engineer joining a codebase loses their first week just figuring out how things work and it costs a senior teammate real time to walk them through it. Mini-Jarvis Onboarder fixes this with a five-agent AI pipeline: a Repo Analyst maps the codebase structure, a Docs Agent extracts setup steps from the README, and three Gemma-powered agents generate a plain-language architecture briefing, 3-5 starter tickets grounded in the actual file tree (not invented files), and a personalized welcome message all in about a minute. The architecture follows a deliberate safety pattern: agents are stateless, the orchestrator runs a fixed deterministic sequence rather than letting an LLM decide what to do next, and every output is a draft nothing is sent until a human reviews and confirms it. Built with FastAPI, Gemma via Fireworks AI on AMD infrastructure, and Docker. A live on-demand Gemma deployment was configured and validated end-to-end during development; the submitted demo runs with a documented mock-mode fallback due to shared GPU capacity constraints during the hackathon window, exercising the identical pipeline logic, JSON hallucination mitigation, and retry handling.
13 Jul 2026
