EN
Start unlimited
Catalog Courses Books Assets Newsletter Merch About Contact Blogs
Cart Sign in Start unlimited
Catalog / All levels / Local AI Agents with Ollama - Autonomous Workflows Without the Cloud
Mammoth Club All levels 8 sections 32 lectures

Local AI Agents with Ollama - Autonomous Workflows Without the Cloud

Start building your first local agent today.

Created by James Dabalus
01
Skill level
All levels
02
Sections
8
03
Lectures
32
04
Instructor
James Dabalus
What's inside

This course includes.

✓
8
Sections
✓
32
Lectures
✓
24
Resources
✓
Certificate of completion
Included
✓
Mobile and desktop access
Included
✓
AI learning assistance
Included
Unlock all courses with our Subscription Bundle! Get unlimited access to entire course library, books and assets. Learn more and subscribe today!
Course content

Curriculum & lectures.

8 sections · 32 lectures
+ 01 Why Run AI Agents Locally 4 lectures
01 What Makes an "Agent" Different from a Chatbot Locked
02 The Case for Local-First AI Locked
03 Where Ollama Fits in the Local AI Stack Locked
04 The Local-Cloud Spectrum Locked
+ 02 Inside the Local Model Engine 4 lectures
01 Model Formats and Inference Engines Locked
02 Quantization and Memory Tradeoffs Locked
03 Context Length and Why Agents Need More of It Locked
04 Model Lifecycle and Concurrency Locked
+ 03 Giving Agents Abilities — Tool & Function Calling 4 lectures
01 The Mechanics of Tool Calling Locked
02 The Agent Loop, Multi-Turn Tool Use Locked
03 Structured Outputs for Reliable Agents Locked
04 Reasoning Transparency, Thinking Traces Locked
+ 04 Extending Agents with the Model Context Protocol (MCP) 4 lectures
01 MCP as the Common Language for Agent Tools Locked
02 Local MCP Servers in Practice Locked
03 MCP Across the Local Agent Ecosystem Locked
04 Trust, Scope, and Governance of Tool Access Locked
+ 05 Memory, Knowledge & Local Retrieval 4 lectures
01 Why Agents Need Memory Beyond the Context Window Locked
02 Embeddings and Local Vector Search Locked
03 Retrieval-Augmented Generation for Private Knowledge Locked
04 Cross-Session Memory in Personal-Assistant Agents Locked
+ 06 Autonomous Workflows & Multi-Agent Orchestration 4 lectures
01 From Single-Turn Answers to Autonomous Task Loops Locked
02 Orchestration Patterns for Multiple Agents Locked
03 Visual Workflow Automation with n8n Locked
04 Case Studies in Local Autonomous Agents Locked
+ 07 Hardware, Performance & Scaling Locally 4 lectures
01 Matching Models to Hardware Locked
02 Budgeting VRAM for Agent Workloads Locked
03 Performance Tuning Levers Locked
04 Deciding When to Reach for the Cloud Locked
+ 08 Privacy, Security & the Road Ahead 4 lectures
01 What Actually Stays Local Locked
02 Network Exposure and Attack Surface Locked
03 Autonomy, Trust, and Human Oversight Locked
04 The Trajectory of Local-First Agents Locked
Description

About this course.

There's a real difference between a model that answers and an agent that acts.

This video course walks through what it takes to build agents that run entirely on your own hardware.

► Understand why agents make sense locally and how the model engine works.

► Give agents abilities through tool calling and Model Context Protocol.

► Add memory, retrieval, and autonomous multi-agent workflows.

► Cover hardware, performance, and scaling locally.

By the end, you'll see how each piece adds up to something that can work on its own.

✅ Lifetime access to all modules.

Instructors

Taught by people who ship.

James Dabalus

James Dabalus

Instructor

James is a versatile IT Technician specializing in Prompt Engineering, Generative AI, Graphic Design, Web Development, Video Editing, and E-learning. With a passion for automation, he continually seeks innovative ways to streamline digital workflows.

Ready to start building?

Start building your first local agent today.

Buy lifetime access →