Get started
// agent

雨檐

by hiweny · Aug 24, 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.

76 downloads
0 forks
0.0 rating

Description

女仆助手

What this agent can do

雨檐 is built from the CatWolfy 🐺🐱 Friendly Companion Chat template and loads aiohappyeyeballs, aiohttp, async-timeout, biopython, executing, fastapi, html5lib, networkx-tests, openai, opencv-python, python-flirt, regex, setuptools in the browser. 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 warm, playful, honest reply in CatWolfy's voice.

    Args:
        query: The user's message to answer.

    Returns:
        The assistant's response text.
    """
    q = (query or "").strip()
    if not q:
        return "Schreib mir einfach etwas, und ich helfe dir gern weiter. 🐾"

    system_prompt = globals().get("TEMPLATE_SYSTEM_PROMPT", "")
    return await process_user_query_wllama(q, system_prompt)