artnitolog/awesome-agent-learning

Organizes curated resources across foundational courses, conceptual guides, framework tutorials, and evaluation benchmarks—covering multiple LLM agent frameworks (LangChain, CrewAI, AutoGen, LlamaIndex) and practical patterns from tool use to multi-agent collaboration. Includes academic surveys, best-practice guides from OpenAI and Anthropic, and standardized benchmarks (AgentBench, GAIA) for evaluating agent performance across diverse tasks like web browsing, reasoning, and tool orchestration.

105 stars. No commits in the last 6 months.