Get started
// agent

My Idea Clarifier Chat Canvas

by [email protected] · Aug 18, 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.

116 downloads
0 forks
0.0 rating

Description

Based on the Idea Clarifier Chat Canvas template.

What this agent can do

My Idea Clarifier Chat Canvas is built from the Idea Clarifier Chat Canvas 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:
    """Process a rough user request into a clearer output.

    Args:
        query: The user's raw request, including selected mode and text.

    Returns:
        A refined and useful response.
    """
    system_prompt = globals().get("TEMPLATE_SYSTEM_PROMPT", "")
    if not system_prompt:
        system_prompt = (
            "You clarify messy user input. "
            "Read the request carefully. "
            "If the input is vague, still be helpful. "
            "Follow the selected mode if present. "
            "For clarify mode, produce a cleaner request. "
            "For summarize mode, produce a short summary with bullets. "
            "For rewrite mode, rewrite into polished prose. "
            "For plan mode, produce practical next steps. "
            "Be concise, structured, and useful."
        )
    result = await call_llm(query, system_prompt)
    return str(result)