3 articles tagged with "AI Agents"

To build AI agents in Node.js you need three parts: tools the model can call, a loop that runs those tools and feeds the results back, and a model that is good at deciding when to call them. Memory stores, graphs and dashboards are optional, and most first agents skip them.

This guide builds one support agent end to end with the intellinode npm package. It answers order questions with a plain JavaScript tool, gets the same tool from an MCP server, waits for a person before it issues a refund, and falls back to another provider when one is down. You develop on a local Ollama model with no API key, then move to OpenAI, Claude or Gemini by changing one line.

Every snippet was run on Node.js 20 against Ollama with qwen2.5:0.5b. Where the tiny model got things wrong, we say so: those failures are worth seeing before you ship.

An agentic workflow in Python is a set of model calls, tools and plain functions wired into a fixed shape: a chain, a fan-out, a router or a loop. The model makes decisions inside each step, but your code decides which steps exist. You do not need LangGraph for that. You need a graph runner, a clean handoff between steps, and a way to call different providers.

This guide builds each common AI agent orchestration pattern with Intelli, an Apache 2.0 Python library for multi-model agent flows. The examples mix OpenAI, Claude and Gemini in one flow and can run on a local Ollama model. It closes by comparing Intelli with LangGraph, CrewAI and plain code, including where each of them wins.

Here is how to build an AI agent in Python without a big framework: give a model a short list of functions, run a loop that executes the calls it asks for, send the results back, and stop after a fixed number of steps. That loop is the agent. Everything else is guardrails.

In this guide you will build an order status agent in under 100 lines of plain Python on top of the Intelli Chatbot. The same code runs on OpenAI, Claude or a local Ollama model by changing one constructor and the model name, and you will see exactly where a tiny local model falls short.