Multi-Agent AI Systems: Build Without CrewAI or AutoGen

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

• RAG systems for your documents
• Voice assistants that work offline
• Code reviewers on every git commit
• Content generators at zero cost
• Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

---

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev

Comments

[BotSailor]

Really enjoyed this approach. There’s something refreshing about seeing a multi-agent setup built from the basics instead of immediately reaching for a framework like CrewAI or AutoGen.

The local Ollama angle is especially interesting—being able to experiment without API keys, recurring costs, or sending everything to a cloud service makes this much more approachable for learning and prototyping.

I also like the idea of understanding what’s happening underneath the abstraction layer. Frameworks can definitely speed things up, but building the pieces yourself first gives you a much better feel for how agents actually communicate and work together. Great practical walkthrough!