Small lessons. Real running code.

Learn agentic AI one concept at a time. Read it, run it, make it yours. Every output on this site came from an actual run.

Find your next framework

32
32 of 32

LangGraph

Build agents as graphs. Loops, memory, human approval and full control of the flow.

AgentsStatefulPython

LangChain

The layer under most agents. Models, tools, prompts and messages in one interface.

FoundationPython

Google ADK

Google's Agent Development Kit, built around Gemini and Vertex AI.

AgentsGoogle

OpenAI Agents SDK

OpenAI's own agent loop, with handoffs, guardrails and tracing built in.

AgentsOpenAI

Claude Agent SDK

Claude Code as a library. File editing, bash and search, ready to run.

Coding agentAnthropic

Semantic Kernel

Microsoft's SDK for wiring models into .NET and Python applications.

Microsoft.NET

Vercel AI SDK

The TypeScript way to build streaming AI apps and agents on the web.

TypeScriptStreaming

CrewAI

Give each agent a role, a goal and a backstory, then let the crew work the task.

Multi agentPython

AutoGen

Microsoft's framework where agents solve problems by talking to each other.

Multi agentMicrosoft

MetaGPT

Agents assigned software company roles: PM, architect, engineer, reviewer.

Multi agentRoles

CAMEL-AI

Research-led framework for studying how large agent societies cooperate.

Multi agentResearch

LlamaIndex

Agents that reason over your documents. Strong on retrieval and indexing.

RAGPython

Haystack

deepset's pipeline framework for search and retrieval heavy applications.

RAGPipelines

DSPy

Stanford's approach: stop writing prompts, compile and optimise them instead.

PromptsResearch

Pydantic AI

Type safe agents. If you already trust Pydantic for validation, this feels like home.

TypedPython

Instructor

Get structured, validated objects back from any model instead of parsing prose.

TypedStructured

n8n

Drag nodes onto a canvas and wire an AI workflow without writing much code.

No codeWorkflows

Langflow

A visual builder for LangChain flows. Drag, connect, export as code.

No codeLangChain

Flowise

Open source drag and drop builder for LLM apps and agents.

No codeOpen source

Dify

A full platform: build, deploy and monitor agents from a browser.

PlatformNo code

AutoGPT

The project that made autonomous agents famous. Give a goal, walk away.

AutonomousGoals

Agno

A fast, lightweight framework for multimodal agents with memory built in.

AgentsMemory

Letta

Formerly MemGPT. Agents that manage their own long term memory.

MemoryStateful

Griptape

Structured agents, pipelines and workflows with control over every step.

AgentsPipelines

smolagents

Hugging Face's tiny agent library. Agents that write and run Python.

MinimalHugging Face

Browser Use

Point an agent at a real browser and let it click, type and read pages.

BrowserAutomation

MCP

Not a framework. The standard that lets any agent plug into any tool or data source.

ProtocolTools

Composio

Hundreds of ready made tool integrations your agent can call, with auth handled.

ToolsIntegrations

LiteLLM

One interface and one proxy in front of a hundred model providers.

GatewayRouting

E2B

Secure cloud sandboxes so an agent can run the code it just wrote.

SandboxExecution

AgentOps

Tracing, cost tracking and replay for agents you have already shipped.

ObservabilityCost

Mastra

The TypeScript agent framework, with workflows, evals and deployment included.

TypeScriptWorkflows