Skip to content
local-ai

Agentic AI & Harnesses

Tool use, agent frameworks, and orchestration with local models.

  1. Advanced

    What is an AI agent?

    An agent is a model given tools and a loop: it reasons, acts, observes the result, and repeats until the job is done. What that means, and where it breaks.

  2. Advanced

    Tool use and MCP

    How a model actually calls a tool, why the Model Context Protocol has become the common way to connect them, and how to keep tool access safe.

  3. Advanced

    Agent frameworks and local models

    The frameworks for building agents, how to choose between them, and how to run them against a local model, with a realistic view of what that combination can do.