Learn GenAI foundations, agent patterns, frameworks, and production operations in one place. Start with fundamentals and work toward real systems.
Curated learning journeys that start with foundations and branch into build and production tracks
New to AI agents? Learn the fundamentals from zero.
Build agents with Python frameworks like LangGraph and CrewAI.
Agent development in the TypeScript ecosystem.
Ship, monitor, and scale agents in production.
See what the hub already covers well, which topics are only partial today, and what should be added next for modern GenAI development.
Models, tools, prompting, structured outputs, and context design.
ExploreRAG, memory, MCP, human review, UX, and product architecture.
ExploreReasoning, orchestration, multi-agent collaboration, and workflow reliability.
ExploreGuardrails, evals, observability, deployment, cost, and governance.
ExploreGenAI and agent building blocks, arranged from fundamentals to advanced systems
Understanding autonomous AI systems that perceive, reason, plan, and act to achieve goals.
Learn moreHow agents interact with external tools, APIs, and services to take action in the real world.
Learn moreHow to choose the right model for each task and route workloads by capability, latency, and cost.
Learn moreGenerating validated JSON, typed objects, and schema-constrained results instead of brittle free-form text.
Learn moreHow prompts, retrieved documents, tool results, memory, and instructions are assembled into the model context.
Learn moreHow GenAI systems work across text, images, audio, video, and documents instead of text alone.
Learn moreShort-term, long-term, and episodic memory architectures that give agents persistent knowledge.
Learn moreA practical framework for choosing whether to adapt the model, retrieve knowledge, call tools, or design a workflow.
Learn moreHow to place approvals, escalation points, and review loops into GenAI and agent workflows.
Learn moreHow to design access control, tenant isolation, and data boundaries for production GenAI systems.
Learn moreThe open standard that lets LLM applications seamlessly connect to any external data source or tool.
Learn moreRetrieval-augmented generation and its evolution into agentic systems with hierarchical retrieval.
Learn moreChain of Thought, ReAct, Tree of Thought, and other reasoning strategies agents use to solve problems.
Learn moreRetries, idempotency, fallback chains, and bounded autonomy for reliable multi-step agent workflows.
Learn moreWhen agents should act through user interfaces and what controls those systems require.
Learn moreCoordinating multiple AI agents to collaborate, delegate, and solve complex problems together.
Learn moreThe most-used agent development frameworks in 2026
Anthropic
Anthropic's production-grade agent runtime with deep MCP integration, computer use capabilities, and a developer-first design philosophy. It provides an agentic loop that automatically handles tool calls, supports multi-turn conversations, and includes built-in guardrails for safe agent behavior.
OpenAI
OpenAI's official SDK for building production-ready agents with managed infrastructure, tool use, handoffs between specialized agents, and built-in guardrails. The SDK is available for both Python and TypeScript and provides a minimal yet powerful set of primitives: Agents, Handoffs, Guardrails, and a Runner to orchestrate everything.
Google's comprehensive Agent Development Kit for building multi-agent systems powered by Gemini and other models. ADK now spans Python, TypeScript, Go, and Java, and provides a layered architecture supporting simple LLM agents, pipeline agents with sequential/parallel/loop workflows, and custom agents with arbitrary orchestration logic. Deep integration with Google Cloud services and Vertex AI.
LangChain Inc.
Graph-based framework for building stateful, multi-actor LLM applications with cycles, controllability, and persistence. LangGraph models agent workflows as state machines where nodes are functions and edges define transitions, including conditional routing. It provides built-in checkpointing, human-in-the-loop support, and seamless LangSmith integration for debugging.
CrewAI Inc.
Role-based multi-agent framework where agents have defined roles, backstories, and goals. CrewAI emphasizes natural collaboration and delegation between agents organized as a 'crew'. It provides a high-level abstraction that makes it easy to create teams of AI agents that work together on complex tasks, with built-in support for sequential and hierarchical processes.
Vercel
TypeScript-first SDK for building AI-powered web applications with streaming, tool use, structured outputs, and multi-model support. The Vercel AI SDK provides three layers: AI SDK Core for server-side LLM calls, AI SDK UI for React/Svelte/Vue chat hooks, and AI SDK RSC for React Server Components streaming. It is a widely used way to integrate AI into web applications.
Proven architectures for building effective agents
Reasoning and Acting — the agent thinks step-by-step, then acts on its reasoning in iterative loops.
Explore patternA central orchestrator agent decomposes tasks and coordinates specialized worker agents.
Explore patternAgents communicate directly without a central orchestrator for exploratory and creative tasks.
Explore patternMulti-layered agent architecture where supervisors manage teams of specialized sub-agents.
Explore patternAgents iteratively use tools based on reasoning to augment their generation capabilities.
Explore patternRole-based agent collaboration where each agent has defined expertise, goals, and communication patterns.
Explore patternStep-by-step tutorials from beginner to production
Built by Sitharaj Seenivasan. This guide is free, open source, and built for the developer community.