Fast LLM & Agents & MCPs
A collection of reference notes and sample code covering LLM fundamentals, retrieval-augmented generation, fine-tuning and agent frameworks, with runnable examples in LangChain, AWS Strands Agents and Google's Agent Development Kit.
This repository is a learning resource covering large language models, agents, tools and the Model Context Protocol, both as reference notes and as runnable sample code. It walks through LLM architectures, retrieval-augmented generation, fine-tuning, prompt engineering and agent frameworks.
Sample projects are grouped by framework: LangChain and LangGraph agents with static tools, structured output, short-term memory, subagents and multi-agent sequential, evaluator and router patterns; AWS Strands Agents examples with a Streamlit interface, local and remote MCP tools, and session management on SQLite; and Google Agent Development Kit examples with FastAPI and Streamlit front ends, memory, and sequential, parallel, loop and hierarchical multi-agent setups.