// topic

#OpenAI

8 guides~48 min totalupdated Oct 14, 2026

Which AI Agent Framework Should You Use in 2026?

A developer's decision guide to the best AI agent frameworks in 2026 — three questions to confidently pick LangGraph, CrewAI, the OpenAI or Claude SDK.

Beginner · 8 min

AI Engineering

Read the guide →

All guides

8 on this page

Intermediate5 minChatGPT MCP: Connect Any MCP Server to ChatGPT (2026) ChatGPT MCP setup in 2026: turn on Developer Mode, add your MCP server as a custom connector over OAuth, and handle the write-confirmation gotcha.Intermediate4 minLLM Structured Outputs: Validated JSON in Python (2026) Get structured outputs from LLMs in Python: validated JSON, not fragile parsing — with Pydantic, OpenAI Structured Outputs, and instructor. Runnable code.Beginner4 minLLM API Keys: Set Up OpenAI, Anthropic & Gemini (2026) An LLM API key primer: where to get OpenAI, Anthropic, and Gemini keys, how to load one safely with python-dotenv, and how to avoid a leaked-key bill.Beginner7 minAI Agent Loop in Python: Build a ReAct Agent From Scratch Build an AI agent loop in Python from scratch: a framework-free ReAct agent that thinks, calls a tool, observes the result, and repeats until the job is done.Beginner7 minAI Agent Memory in Python: Short-Term Memory From Scratch Add AI agent memory in Python from scratch: keep the conversation in a messages list, then trim and summarize older turns to fit the model's context window.Beginner6 minCall an LLM in Python: The First Building Block of an Agent Call an LLM in Python with real OpenAI and Anthropic code: system vs user prompts, temperature, JSON output, and why one call isn't yet an agent.Beginner7 minTool Calling in Python: Make an LLM Use Your Functions Tool calling in Python from scratch: define a tool, parse the model's request, run your function, and return the result — with real, current OpenAI code.

Following #OpenAI?

Get new #OpenAI guides the day they publish. One email, no spam.