Powered by NVIDIA NIM

AI that browses
the web for you

Give it a task in plain English. It plans with a 120B model, executes in a real browser, and streams every action live to your screen.

Six NVIDIA Models. One Agent.

Planner
nemotron-super-49b
Executor
llama-3.1-nemotron-70b
Fallback
llama-nemotron-8b
Embeddings
nv-embedqa-1b
Reranking
nv-rerankqa-1b
Vision
llama-3.2-90b-vision
🧠

Multi-Model AI

Six specialised NVIDIA models — planner, executor, vision, embeddings, reranking, and fallback — working in concert.

🌐

Real Browser

Full Playwright automation — click, type, scroll, navigate, screenshot — on any public website.

📡

Live Streaming

Every action streams to your browser in real time via WebSocket. Watch the agent work step by step.

🧩

Vector Memory

Embedding-based memory recalls past task results so the agent improves over time.

📋

AI Summaries

After each task the agent writes a plain-English summary of what it found and did.

👁️

Vision Analysis

Screenshots are interpreted by the vision model to verify state and recover from errors.