unknown

A 12-lesson educational repository teaching AI agent fundamentals by building one agent incrementally from scratch using local LLMs. Covers core concepts like structured output, tool usage, agent loops, memory systems, planning, atomic actions, and observability without frameworks or cloud APIs. Emphasizes transparency and mechanical understanding over abstraction, progressing from basic LLM calls through decision-making, execution patterns, and testing methodologies.

pguso/agents-from-scratch: Build AI agents from first principles using a local LLM

Welcome to AI Hub, the go-to Squad for developers, researchers, and enthusiasts passionate about AI. Whether you're just starting your journey or already building cutting-edge models, this is your place.