How to Build Your Own AI Agent (Like PewDiePie)

PewDiePie is building his own AI assistant, Odysseus, and training a local model, Ajax, to power it. In this video I break down what Odysseus is, how an agent harness works from scratch, what it actually means to run a model locally with llama.cpp and Hugging Face, and how you can fine-tune a small model like Qwen 3.5 9B on agent traces so it calls tools reliably in your own harness. --- 🔗 *Links* - Odysseus (GitHub): https://github.com/odysseus-dev/odysseus - Claude system prompts: https://platform.claude.com/docs/en/release-notes/system-prompts - Hugging Face models: https://huggingface.co/models - Hugging Face hardware settings: https://huggingface.co/settings/hardware - Llama macOS app (llama.cpp): https://github.com/ggml-org/Llama-macOS - llama.cpp: https://github.com/ggml-org/llama.cpp - Qwen3.5-9B (Unsloth GGUF): https://huggingface.co/unsloth/Qwen3.5-9B-GGUF - Kolibri 1: https://huggingface.co/Aleph-Alpha/Kolibri-1 - Qwen3.8-27B: https://huggingface.co/Qwen/Qwen3.8-27B - Agent trace datasets: https://huggingface.co/datasets - Post-training agents playlist: https://www.youtube.com/playlist?list=PLo2EIpI_JMQvQZm-kVlz4wY1vWF0LBcf5 --- 🤓 *Topics Covered* - What PewDiePie's Odysseus is and how it works - How AI agent harnesses and tool calling work - Running and fine-tuning small local models --- ⏱️ *Timestamps* 0:00 Intro 1:18 What Is Odysseus 4:27 What Is an Agent Harness 10:30 Running Local Models 16:51 Training Small Models 👋 *Connect with me* My website: https://alejandro-ao.com/ X (Twitter): https://x.com/_alejandroao LinkedIn: https://www.linkedin.com/in/alejandro-ao/ Courses: https://aibootcamp.dev/