ollama-local

What problem does it solve?

This Skill allows you to manage and interact with Large Language Models (LLMs) running locally on your machine using the Ollama platform, enabling powerful AI capabilities without relying on external cloud services.

Core Features & Use Cases

• Model Management: Easily list, pull, and remove Ollama models.
• Inference: Perform chat-based conversations and text completions with local LLMs.
• Embeddings: Generate vector embeddings for text, useful for semantic search and retrieval.
• Tool Use: Leverage models capable of function calling for structured interactions.
• Sub-Agent Integration: Spawn local LLM-powered sub-agents within the OpenClaw framework for complex workflows.
• Use Case: You can use this skill to run a coding assistant locally to review your code, generate documentation, or answer technical questions, all while keeping your data private.

Quick Start

List all the Ollama models you have installed by running python3 scripts/ollama.py list.