The definitive open-source guide to every framework, pattern, and tool for AI agent development. From first steps to production.
Curated learning journeys for every experience level
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.
The fundamentals of AI agent development
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 moreShort-term, long-term, and episodic memory architectures that give agents persistent knowledge.
Learn moreChain of Thought, ReAct, Tree of Thought, and other reasoning strategies agents use to solve problems.
Learn moreCoordinating multiple AI agents to collaborate, delegate, and solve complex problems together.
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 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. It 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. It 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 the most popular 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.