Get started
// agent

JARVIS

by [email protected] · Sep 29, 2026 Public

Choose how to run this agent

⚡ Local runs on your GPU. For usable speed it needs a WebGPU-capable browser — Chrome or Edge on a machine with a graphics card, or an Apple Silicon Mac. Without a supported GPU, pick OpenAI or Anthropic above instead. Check your machine
Try it now

Requires an API key and an AgentOp account.

0 downloads
0 forks
0.0 rating

Description

JARVIS es un asistente de inteligencia artificial avanzado, diseñado para ayudarte con tus preguntas, tareas y problemas de forma rápida, inteligente y eficiente. Mantiene la calma, analiza cada situación y combina precisión y elegancia.

What this agent can do

JARVIS is built from the Everyday AI Chatbot template. Runs fully on your own device: llama.cpp compiled to WebAssembly, GPU-accelerated through WebGPU, with no API key and no server. After the one-time model download it works offline. Can run on OpenAI models with your own API key, encrypted in your browser. Can run on Anthropic Claude models with your own API key, encrypted in your browser.

Source Code

agent.py 
async def process_user_query(query: str) -> str:
    """Generate a helpful chatbot reply.

    Args:
        query: The user's chat message.

    Returns:
        The assistant reply as plain text.
    """
    prompt = f"User message:\n{query.strip()}\n\nWrite a helpful reply."
    answer = await agentop_llm.generate(prompt, globals().get("TEMPLATE_SYSTEM_PROMPT", ""))
    return answer.strip()