Episode Details

Build & Automate Anything with DeepSeek V4 (Free): Chat Apps, AI Agents, OpenCode, Hermes, Agent ZeroThe video shows how to access and use DeepSeek V4 for free to build apps and automate tasks, starting in the DeepSeek chat by switching between Instant and Expert mode, enabling DeepThink and optional web search, and generating runnable “single HTML” projects that can be previewed or downloaded. The presenter demonstrates creating a Pomodoro timer and simple games (Pong and others) in minutes, then explains using Ollama to run DeepSeek V4 Flash in the cloud within token limits and connect it to multiple agent/coding tools such as OpenCode, ChatGPT Codex, OpenClaw, and Hermes, including scheduling daily research tasks, Telegram control, and browser automation. They discuss improving agent personalization by recording work with OMI and syncing to an Obsidian vault for memory/context, compare model/API cost and capability differences (Flash vs Pro and other models), and show setting up Agent Zero via Docker and OpenRouter to use DeepSeek models, with an invitation to learn more in the AI Profit Boardroom.00:00 DeepSeek V4 Overview00:14 Chat Modes and Settings00:57 Build a Pomodoro Timer01:56 Build a Pong Game02:50 Install Llama for Agents04:09 Choose V4 Flash Model04:53 Preview and Download Apps06:27 Five Terminal Agent Setup08:19 Connect Coding Agents12:32 Run Prompts Across Agents14:24 Failures and Best Harness18:21 Personal Context with OMI20:34 Live Q&A and Tips22:34 Best Use Cases Recap26:02 DeepSeek Setup Options26:45 Hermes Scheduled Tasks28:07 Telegram Remote Control28:55 Browser Automation Agents30:22 API Cost Comparisons35:47 Model Benchmarks Breakdown40:41 Install Agent Zero42:36 Connect DeepSeek via OpenRouter47:35 Local Models and Memory51:47 Wrap Up and Resources