.png&w=256&q=75)
🤝 Top Collaborators
🤓 Latest Submissions
CrowdSeed AI
Inspiration In 2016, a landmark research paper proved that human crowds design significantly better robots when they can observe and iterate on each other's work ("Social" condition) compared to working in isolation ("Independent" condition). The social group unlocked a hidden "design quality" factor—largely driven by symmetry—that helped their robots walk farther. With the rise of agentic workflows, we asked a fundamental question: Does the "wisdom of the crowd" still hold true when the crowd is entirely made of AI agents? What It Does CrowdSeed AI is a simulation engine and interactive Streamlit platform that reruns this exact behavioral experiment using LLMs instead of humans. Agents are placed in a 5x5 grid environment and tasked with drawing connected lines to form a rigid robot body. The robots are then evaluated in a physics simulator to see how far they can walk. We split our AI agents into two distinct experimental tracks: - Independent Group (Control): Agents can only see and iterate on their own past design attempts. - Social Group (Experimental): Agents can view, adapt, and build upon the successful designs of their peer agents. How We Built It - Agent Infrastructure: Multi-agent LLM framework orchestrated to handle memory, and sequential design generations. - Physics & Evaluation Engine: A customized 2D physics evaluation layer that scores the distance traveled by each generated 5x5 grid robot. - Frontend & Analytics Dashboard: A Streamlit web application featuring results. What We Discovered (Our Real Results) Design Quality & Latent Factors: The Social AI agents scored significantly higher on the computed "design quality" factor than the independent agents (p = 0.0002, indicating a statistically significant result). Value & AI Infra Impact CrowdSeed AI provides the infrastructure to benchmark and study "artificial culture" and social synergy, proving that social connectivity makes AI agent swarms fundamentally more creative and capable.
16 Sep 2026
SignalForge
SignalForge is an autonomous AI-powered options paper-trading agent built on Alpaca. It continuously scans a diversified watchlist for market opportunities using technical indicators such as momentum, moving averages, RSI, MACD, and volume. Promising signals are evaluated by Azure OpenAI, which produces a structured trading decision, confidence score, direction, and supporting rationale. Before any order is submitted, a deterministic risk engine independently checks market status, AI confidence, portfolio exposure, position limits, recent losses, liquidity, bid-ask spread, option expiration, premium, and position size. Approved opportunities are converted into suitable call or put contracts and submitted to Alpaca’s paper-trading API. The agent then monitors open positions and applies defined stop-loss, take-profit, expiration, and maximum-holding-period rules. A real-time web dashboard displays portfolio performance, AI decisions, risk evaluations, positions, order history, scanner results, system configuration, and agent status. SignalForge also integrates Alpaca’s CLI, uses Supabase PostgreSQL for persistent records, and provides manual controls, authorization protection, and an emergency kill switch.
4 Sep 2026
Job Pulse Ai
JobPulse AI is an AI-powered resume and skill-gap analyzer built to help students, fresh graduates, and job seekers better understand their readiness for a target role. Users can upload their resume in PDF format and provide a target job description. The application analyzes both inputs to calculate an overall fit score, identify important missing skills and keywords, and highlight areas where the candidate can improve. It then generates a personalized 7-day learning plan focused on the identified gaps, helping users turn their weaknesses into actionable learning goals. JobPulse AI transforms the traditional job application process into a personalized, data-driven experience that helps candidates understand where they stand and what they should learn next.
10 Aug 2026
