AnthropicGoogle GeminiOpenAI

One Agent, Three SDKs

Build the same AI agent three ways — in the Anthropic (Claude), Google (Gemini), and OpenAI (GPT) SDKs, side by side — and learn the shared shape underneath all of them.

The premise: every module teaches one agent concept and builds it three ways at once. You see exactly where the providers agree, where they differ, and why — so switching SDKs becomes a config change, not a rewrite.

The running example: Acme Support, a customer-service agent for a fictional online store. Each module adds one real capability — a tool, structured output, memory, retrieval, multi-agent routing — and builds it in all three SDKs.

Every example is complete and runnable, in both Python and Node.js, with model IDs and package names verified against current official docs.

The 8 Modules

M00

Setup & Three Clients

Install all three SDKs, wire up keys, and send the same "hello" to each. Meet the universal agent pipeline.

Ready
M01

The Agent Loop & Tool Use

Give Acme its first tool and write the tool-use loop by hand in all three SDKs. The engine under every framework.

Ready
M02

Structured Output

Force each SDK to return a typed, schema-validated OrderStatus object — guaranteed JSON, not prose.

Ready
M03

Multi-Tool Orchestration

Add product search and refunds. Many tools, parallel calls, and loop-until-done across the three SDKs.

Ready
M04

Memory & Conversation

Stateless history vs. chat sessions vs. server-stored state — three takes on remembering the customer.

Ready
M05

RAG / Retrieval Grounding

Ground Acme's answers in a help-doc knowledge base with embeddings and retrieval, three ways.

Ready
M06

Multi-Agent Systems

A triage agent routes to Orders and Refunds specialists — via subagents, the Agents SDK, and Google ADK.

Ready
M07

Production

Streaming, retries, cost, and each provider's agent framework as the graduation. Ship Acme Support.

Ready