AI Agents Framework

Experiments with autonomous AI agents: - Built agent architecture with planning, reasoning, and action execution - Implemented tool use interface for external systems and APIs - Designed memory system for multi-step task context - Created evaluation framework for testing agent performance - Explored prompting strategies (Chain-of-Thought, ReAct) - Built examples across different domains **Learning project**: Understanding how agent architectures work, not building production agents. Early exploration of LLM-based agents and their capabilities/limitations.