🎥 Video demo

Autonomous Web Browsing AI Agent with Vision - powered by MultiOn

As of May 6, MultiOnChat is now MultiAgent and frontend and backend repositories have been merged!

• git
• Python 3.11
• pipenv
• Node 21
• pnpm

1. Clone this GitHub respository:

git clone https://github.com/justinsunyt/multiagent.git

1. Create an account on Supabase if you don't have one already.

2. Create a project.

3. In Table Editor, create a table called chats with the following columns:

Make sure last_chatted and session_id are nullable.

4. Create the following auth policy for chats:

5. In Authentication -> Providers, enable Email as an auth provider.

1. Navigate to the backend/ folder:

cd backend

2. Create a .env file in the backend/ folder and store the following variables:

SUPABASE_URL="<Supabase project URL>"
SUPABASE_KEY="<Supabase anon key>"
SUPABASE_JWT_SECRET="<Supabase JWT secret>"
SUPABASE_JWT_ISSUER="<Supabase project URL>/auth/v1"
REPLICATE_API_TOKEN="<Replicate API token>"
GROQ_API_KEY="<Groq API key>"
MULTION_API_KEY="<Multion API key>"

3. Launch pipenv environment:

pipenv shell

4. Install required packages:

pipenv install

5. Run the FastAPI development server:

uvicorn main:app --reload

1. Navigate to the frontend/ folder:

cd frontend

2. Create a .env.local file in the frontend/ folder and store the following variables:

NEXT_PUBLIC_SUPABASE_URL="<Supabase project URL>"
NEXT_PUBLIC_SUPABASE_ANON_KEY="<Supabase anon key>"
NEXT_PUBLIC_PLATFORM_URL="<deployed backend URL, will only be used in production>"

3. Install required packages:

pnpm install

4. Run the Next.js development server:

pnpm dev

Finally, open https://localhost:3000 with your browser to start using MultiAgent!

• Client: Next.js, TanStack Query
• UI: Tailwind, shadcn/ui, Framer Motion, Lucide, Sonner, Spline
• Server: FastAPI
• Database: Supabase
• AI: MultiOn, Replicate, Groq

• Autonomously browse the internet with your own AI agent using only an image and a command - order a Big Mac, schedule events, and shop for outfits!
• Supabase database and email authentication with JWT token verification for RLS storage
• Currently supports llama3-70b, llava-13b, lava-v1.6-34b, qwen-vl-chat

• Llama tool calling to activate agent whenever appropriate
• Refine image prompt recursively with Llama
• Chat selection menu to choose between any combination of LLMs and VLMs
• Toggle MultiOn local mode
• Deploy! (You will have to use your own API keys)

Special thanks to MultiOn for the epic agent package and auroregmbt for the Spline animation!