.png&w=256&q=75)
🤝 Top Collaborators
.png&w=640&q=75)
🤓 Latest Submissions
Cloudrise Alphaca Ai trading app
CloudRise is an autonomous, explainable options trading agent built for Alpaca’s paper-trading environment. It is designed around a simple principle: the system that discovers a trading opportunity should not have unrestricted authority to move capital. Many automated trading systems place market analysis, risk management and order execution inside one opaque decision process. CloudRise separates these responsibilities into independent layers. Research agents may propose a trade, but only a deterministic Risk Governor can authorize it. The execution layer cannot bypass either component. Every 15 minutes, CloudRise analyzes SPY, QQQ and IWM using market data supplied by Alpaca. These liquid index ETFs were selected because they typically offer deeper options liquidity and avoid the company-specific earnings risks associated with individual stocks. Four specialist agents independently evaluate every candidate: The Regime Agent compares short- and medium-term exponential moving averages to identify the prevailing market direction. The Momentum Agent evaluates recent price returns and the strength of directional movement. The Breakout Agent determines where the current price sits relative to its recent trading range. The Reversion Agent uses RSI to detect exhaustion and veto potentially overcrowded entries.
4 Sep 2026
Claption
Claption is a containerized video captioning app built for the AMD Developer Hackathon ACT II Video Captioning track. It processes short video clips by sampling frames with FFmpeg, generating a grounded visual fact sheet with Fireworks AI, and then rewriting that factual summary into four required caption styles: formal, sarcastic, humorous-tech, and humorous-non-tech. To improve leaderboard performance, Claption separates factual understanding from tone generation, then uses an internal LLM judge loop to score captions for accuracy, tone match, humor quality, and hallucination risk. Weak captions are automatically repaired before final export. The project includes a Next.js demo app, batch CLI, Docker container, sample outputs, and judge-ready setup instructions.
13 Jul 2026
