Back to projects
Multi-Agent Debate System
An AI-powered multi-agent debate platform built with FastAPI and local Ollama LLMs, featuring a modern Vite, React, and Tailwind CSS frontend.
PythonFastAPIOllamaViteReactTypeScriptTailwindCSS
Developed an interactive multi-agent debate platform designed to orchestrate structured, multi-perspective discussions between autonomous AI agents. Built as part of the Data & AI coursework, the system leverages local LLM orchestration via Ollama to execute privacy-focused, low-latency agent interactions.
Engineered an asynchronous Python and FastAPI backend to manage agent turn-taking, argument synthesis, and real-time state orchestration. Built a reactive UI with Vite, React, TypeScript, and Tailwind CSS to provide dynamic, live streaming visuals of debates as they unfold.