The Challenge: Track 1 demanded an agent that could clear a strict 80% accuracy gate across 8 complex categories while burning the absolute minimum number of Fireworks API tokens. The catch? The agent ...
Gemini AI GPT-3.5 AI/ML API DeepSeek V3 Anthropic Claude ...
People fail interviews less on skill than on nerves — rambling, saying "um", going monotone, or giving no concrete results — and text-based AI prep ignores how you speak, which is half of what an ...
This project introduces a highly resilient, cost-optimized AI routing architecture designed to maximize token efficiency without sacrificing accuracy. Built entirely in asynchronous Python to ensure ...
vinci-monsoon is a production-ready, token-optimized hybrid routing system engineered specifically for Track 1 of the AMD Developer Hackathon. The system utilizes a dual-lane architecture designed to ...
CineScribe is a multi-modal video intelligence system that processes video content and produces human-like captions in multiple stylistic voices — formal, sarcastic, humorous with tech references, and ...
PADAYON is an AI learning partner built for Filipino students who struggle with academic English, messy notes, and last-minute studying. Instead of simply giving answers, PADAYON organizes what the ...
Most agents answer every question the same expensive way, burning the same budget on a trivial lookup as on a hard proof. TokenMiser doesn't. It treats cost as a first-class objective, matching each ...
This agent is built for the AMD Developer Hackathon (ACT II) Track 1. It reads an array of tasks from a JSON input file, intelligently routes each task through a multi-stage pipeline, and writes ...
This project is a Dockerized general-purpose AI agent built for Track 1 of the AMD Developer Hackathon: ACT II. It reads batches of natural language and coding tasks from /input/tasks.json and writes ...
adorable_router — token-efficient LLM routing system adorable_router is a local-first inference router designed to minimize billed tokens while maintaining high accuracy. Instead of sending every task ...