LeonKinda Tired@LeonKindaTired

Voice Thinking Partner helps you think through difficult decisions out loud—without telling you what to do. Speak naturally about a job offer, move, purchase, relationship, or any other decision. The voice agent listens in real time and asks focused follow-up questions when it detects unexamined assumptions, unsupported claims, missing alternatives, or unclear success criteria. Instead of giving advice, ranking options, or making recommendations, it helps make your own reasoning visible. During the conversation, the app captures claims, assumptions, options, and criteria. When the session ends, it turns those observations into a structured, shareable decision map based entirely on what you said. Built with React, Vite, and AssemblyAI’s Voice Agent API, Voice Thinking Partner combines natural voice interaction with structured too calling to create a more reflective and user-controlled decision-making experience.

AlphaPilot is an autonomous AI trading agent designed to identify, evaluate, execute, and manage options trades in Alpaca paper trading. Instead of relying solely on an LLM or a traditional quantitative strategy, AlphaPilot combines both approaches. A quantitative strategy continuously scans the market for potential opportunities using market conditions, momentum, volatility, and options-specific signals. Candidate trades are then passed to an AI supervisor that evaluates the setup, market context, thesis, confidence, and potential risks. The AI does not have unrestricted control over execution. Every proposed trade must pass through a deterministic risk engine that acts as the final authority. Position sizing, portfolio exposure, maximum positions, daily loss limits, drawdown limits, concentration limits, and execution constraints are enforced independently of the AI's decision. The agent operates through an autonomous loop: scan the market → calculate features → generate signals → evaluate with AI → validate through risk controls → execute → monitor positions → repeat. AlphaPilot also maintains a decision journal that records the reasoning behind each trade, allowing users to trace a decision from the original market signal through AI analysis, risk validation, execution, and outcome. The project includes a control dashboard where the agent can be started, stopped, monitored, and configured. Users can inspect live portfolio performance, open positions, trades, risk exposure, agent activity, and historical decisions from a single interface. The goal is not simply to build an AI that can generate trading ideas, but to demonstrate a complete, testable autonomous trading system where AI reasoning is combined with quantitative signals, deterministic safety controls, transparent decision-making, and continuous paper-trading execution.

Six Matches. One leaderboard. Build on AMD, earn points and compete for prizes.

🌎 Online Hackathon | 💻 Month-long challenge | Dates: Sep 1–30, 2026 | 🏆 $10,000 Prize Pool ($5k cash + $5k in AAI credits) A month-long online challenge run by lablab.ai together with AssemblyAI, the Voice AI infrastructure company for builders. Every participant builds on AssemblyAI. You can join at any point — registration stays open for the whole build window, so you can start on day one or pick the project up halfway through and still submit. 🌍 Fully online hackathon. Join and build from anywhere in the world.

🌎 Online Hackathon | 💻 Dates: 28 August–4 September 2026 | 🏆 $6,000 Prize Pool Build AI trading agents on Alpaca — autonomous agents and trading apps using Alpaca's Trading API, MCP server and CLI. 🌍 Fully online hackathon. Join and build from anywhere in the world.