AgentOp
Run a real LLM in your browser with no install or server
AgentOp lets you build AI agents that run entirely in your browser. Open models like Llama, Qwen, Gemma, and Phi load locally with WebGPU. No install, no server, no API key, and your prompts never leave the tab.
You write your agent's logic in Python, test it instantly against a local model, then export everything—as a single standalone HTML file including the model loader, code, UI, and encryption. You can email it, embed it, or run it offline; it works on any machine with nothing to install.
If you prefer GPT-4 or Claude, you can bring your own key (encrypted client-side). Or just describe the agent you want in plain English and AI writes the template for you. Free to start.
