🤓 Latest Submissions
VoiceDesk AI
VoiceDesk AI is a real time voice support agent that feels like calling a helpdesk, except the agent can actually see what you see. A user opens the web app, starts a call, and talks to an AI assistant with a photorealistic avatar that speaks back with lip sync and sub second response times.The agent watches the user's shared screen so it understands the actual problem instead of relying on a vague description. When a user says their account is blocked, the agent reads the error on screen, confirms the issue, and calls a tool to unblock the account directly. Once the issue is resolved, it sends a ticket summary by email so there is a record of the session.Under the hood the agent runs as a LiveKit worker built from independently chosen best in class providers: AssemblyAI for streaming speech to text with end of turn detection, Groq running a vision capable Qwen model for fast reasoning over both speech and screen frames, Deepgram Aura for low latency text to speech, Silero for voice activity detection, and Beyond Presence for the avatar. The frontend is a Next.js app that publishes the user's microphone and screen and renders the avatar in the browser.VoiceDesk AI shows what a modular voice pipeline can do beyond simple question answering: a support agent that sees, listens, reasons, and takes real action on a user's behalf.
30 Sep 2026
Quant Trading Agent
Quant Trading Agent is an autonomous AI trading desk designed to operate on a dedicated Alpaca paper-trading account. It works in two core modes: Entry and Defense. Entry Mode: The agent analyzes a focused set of proven technical indicators, including RSI, MACD, Bollinger Bands, and moving-average crossovers, to generate a bullish, bearish, or neutral market signal with a conviction score. When a trade opportunity is identified, the agent expresses that view through an options trade using a long call for bullish signals and a long put for bearish signals while selecting a real, tradable near-the-money contract. Defense Mode: Once positions are open, the agent continuously monitors portfolio risk, including capital at risk, realized volatility, and drawdown. It can automatically take profits, stop out losing positions, exit contracts approaching expiration, and deploy protective strategies such as a protective put, covered call, or two-leg collar when risk exceeds predefined thresholds. This continuous risk management is what makes the system more than a simple signal-generation bot—it functions as an autonomous trading desk. Every entry and defense decision is accompanied by a plain-language explanation generated by an LLM, with a deterministic fallback to ensure the system remains operational even when the LLM or network is unavailable. All decisions and trades are recorded in an auditable “Why this trade?” trail. The entire system is presented through a live trading terminal dashboard, featuring portfolio KPIs, interactive TradingView candlestick charts, an AI Council multi-agent decision panel, trade explorer, out-of-sample strategy lab, and a one-click watchlist scanner covering 20 tickers. The platform is deployed online through Streamlit Community Cloud.
4 Sep 2026
