I've been building a simple framework to run Ollama-based LLMs with full agentic tooling, entirely on your local machine. I'm calling it # WyvernClaw 🐉 It has:
A new local framework called WyvernClaw has been developed to run Ollama-based LLMs with full agentic capabilities. This framework includes features such as configurable subagents, customizable system prompts, selectable tools like web search and HTTP fetching, and robust sandboxing for file operations and network requests to ensure security. AI
IMPACT Enables users to run advanced AI agentic tooling locally, enhancing privacy and control over LLM operations.