OpenCode Tutorial for Beginners: Setup, Agents, Skills & MCP

Master OpenCode from scratch and learn how to build real-world AI applications using multiple models—without vendor lock-in or expensive subscriptions. This complete OpenCode course covers everything you need to go from beginner to advanced, including setup, model integration, agent workflows, and real project building. You’ll learn how to use OpenCode with tools like Ollama for running models locally, and OpenRouter for accessing multiple cloud models—all in a single workflow. We’ll also explore how to use powerful open models like Gemma 4 and optimize cost using model switching strategies. 🔥 What you’ll learn: OpenCode setup (Windows, Mac, Linux) Local AI with Ollama Cloud models via OpenRouter Multi-agent workflows (Plan vs Build mode) Cost optimization techniques Building real apps (REST APIs, UI apps, automation tools) Sessions, debugging, and workflow management 🎯 Who this is for: Developers & engineers AI enthusiasts Startup founders Anyone building AI-powered applications If you want full control over your AI stack—this is the course to start with.

Claude Code Tutorial: Beginner to Advanced in 20 Minutes. Join our FREE community with free prompts & guides: https://www.skool.com/ai-launchpad/about Chapters: 0:00 - Intro 1:10 - What is Claude & Setup 3:54 - Plan mode & prompting 6:18 - First results & Iteration 8:18 - Claude.md & MCP 12:12 - Context management & extended thinking 16:10 - Deploy your builds 17:07 - Skills & Hooks & Routines 18:39 - Outro For business inquiries including sponsorships and collaborations, please email: business@zinhomedia.com

🔥 Entre para a minha comunidade de automação - https://link.devaprender.com/entrar Curso Claude Code - https://youtu.be/KoFOPpUWi98 Curso Github Copilot - https://youtu.be/uW5OzVgtofU ✅Quer pedir um orçamento de um BOT(robô) ou sistema? - Solicite aqui: https://devaprender.com/orcamentos/ ✅Curso lógica de Programação: https://youtu.be/epf-WQdVis0 Links mencionados no video ------------------------------------------------------------------------------------------ nodejs download - https://nodejs.org/en/download opencode download - https://opencode.ai/download opencode mcp - https://opencode.ai/docs/mcp-servers/#context7 Skills - https://skillsmp.com/ ------------------------------------------------------------------------------------------ Resumo⤵️ Nesse curso completo de OpenCode, eu vou te mostrar como usar essa ferramenta de IA, para se conectar a qualquer provedor de IA, como o OpenAI, Claude Code, DeepSeek, OpenRouter. Ou seja, tanto opções pagas, como opções gratúitas! Aqui você irá aprender a usar o OpenCode do zero, desde de como instalar, configurar um provedor e personalizar e usar as principais funcionalidades como escolher modelos, nível de raciocínio, usar skills, usar servidores mcp e até mesmo como monetizar esse conhecimento. CONTATO COMERCIAL(não respondo dúvidas de videos) ------------------------ jhonatan@devaprender.com 00:00 - O que iremos aprender 00:50 - Como instalar OpenCode 03:18 - Por que usar OpenCode vs Claude Code ou outros? 04:39 - Como instalar qualquer provedor PAGOS 08:43 - Como instalar qualquer provedor GRATUITO 11:33 - Como usar Servidores MCP 14:49 - Como personalizar o OpenCode 16:25 - Como usar SKILLS 19:09 - Quando usar OpenCode no meu fluxo de trabalho? 20:10 - Como monetizar o conhecimento de criação de apps/automações?(parte 1) 20:51 - Como usar o modo Plan/Edit 21:05 - Como monetizar o conhecimento(parte 2) 21:48 - O que estudar a partir de agora?

An overview and starting point for Claude Code. Check out my coding with AI course: https://www.codingwithaicourse.com/ $100 Neon Credits: https://get.neon.com/6uuwMG3 Follow Neon to not miss course giveaways: - X/Twitter: https://x.com/neondatabase - Linkedin: https://www.linkedin.com/company/neondatabase Github Gist With Prompts: https://gist.github.com/bradtraversy/9937e0ecfc8a5b269ce6a885636670dc Crypto Dash Repo: https://github.com/bradtraversy/crypto-dash Timestamps: 0:00 - intro 2:23 - What Is Claude Code 3:56 - Installing Claude 6:43 - First Launch 7:26 - Models & Usage Limits 10:44 - Effort 11:14 - Using Claude In VS Code 12:16 - The First Prompt 16:10 - Shell Mode 17:30 - Modes 19:15 - Settings & Permissions 22:55 - VS Code Extension 24:05 - Refactoring Code 27:03 - Context, Tokens & Clearing 29:20 - Global Sessions 33:14 - Working on an Existing Project 35:48 - Claude.md File & /init 39:28 - Plan Mode 44:58 - Adding Favorites Feature 48:05 - Skills 53:27 - MCPs 57:51 - Sub-Agents

Get started with Codex, OpenAI’s coding agent, in this step-by-step onboarding walkthrough. You’ll learn how to install Codex, set up the CLI and VS Code extension, configure your workflow, and use Agents.md and prompting patterns to write, review, and reason across a real codebase. This video covers: Installing Codex (CLI + IDE) Setting up a repo and getting your first runs working Writing a great Agents.md (patterns + best practices) Configuring Codex for your environment Prompting patterns for more consistent results Tips for using Codex in the CLI and IDE Advanced workflows: headless mode + SDK Start here Sign up: https://openai.com/codex/ Codex overview + docs: https://developers.openai.com/codex Codex Cookbook: https://cookbook.openai.com/topic/codex Install + setup VS Code extension: https://marketplace.visualstudio.com/items?itemName=openai.chatgpt Agents.md standard: https://agents.md Agents.md repo: https://github.com/agentsmd/agents.md Prompting + workflows Prompting guide: https://developers.openai.com/codex/prompting/ Exec plans (Agents.md patterns): https://cookbook.openai.com/articles/codex_exec_plans Config reference: https://github.com/openai/codex/blob/main/docs/config.md#config-reference Updates Changelog: https://developers.openai.com/codex/changelog Releases: https://github.com/openai/codex/releases

Learn to use Anthropic's Claude Agent SDK (formerly Claude Code SDK) for AI-powered development workflows! https://platform.claude.com/docs/en/agent-sdk/overview https://x.com/trq212 **AI Summary** This workshop by Thariq Shihipar (Anthropic) details the architecture and implementation of the **Claude Agent SDK**. The session moves from high-level theory—defining "agents" as autonomous systems that manage their own context and trajectory—to a live-coding demonstration. Shihipar builds an agent "Harness" from scratch, implementing the core **Agent Loop** (Context Thought Action Observation), integrating the **Bash tool** for general computer use, and demonstrating **Context Engineering** via the file system to maintain state across long tasks. **Timestamps** 00:00 Introduction: Agenda and the "Agent" definition 05:15 The "Harness" concept: Tools, Prompts, and Skills 10:10 Live Coding Setup: Initializing the Agent class and environment 15:45 implementing the "Think" step: Getting the model to reason before acting 25:20 The Agent Loop: connecting `act`, `observe`, and `loop` 33:10 Tool Execution: Handling XML parsing and tool inputs 42:00 The "Bash" Tool: Giving the agent command line access 49:30 Safety & Permissions: "ReadOnly" vs "ReadWrite" file access 58:15 Context Engineering: Using `ls` and `cat` to build dynamic context 01:05:00 The "Monitor": Viewing the agent's thought process in real-time 01:12:45 Handling "Stuck" States: Feedback loops and error correction 01:21:20 Multi-turn Complex Tasks: Building a "Research Agent" demo 01:35:10 Refactoring patterns: "Hooks" and deterministic overrides 01:48:39 Q&A: Reproducibility, helper scripts, and non-determinism 01:50:31 Q&A: Strategies for massive codebases (50M+ lines) 01:52:00 Closing remarks and future SDK roadmap * **Evolution of AI Capabilities:** Shihipar argues we are shifting from **LLM Features** (categorization, single turn) to **Workflows** (structured, multi-step chains like RAG) to **Agents**. He defines agents as systems that *"build their own context, decide their own trajectories, and work very autonomously"* rather than following a rigid pipeline. * **The Claude Agent SDK Architecture:** The SDK is built directly on top of **Claude Code** because Anthropic found they were *"rebuilding the same parts over and over again"* for internal tools. * **The Harness:** A robust agent requires more than just a model; it needs a "Harness" containing Tools, Prompts, a **File System**, Skills, Sub-agents, and Memory. * **Opinionated Design:** The SDK bakes in lessons from deploying Claude Code, specifically the "opinion" that general computer use (Bash) is often superior to bespoke tools. * **The Power of the Bash Tool:** A key technical insight is that the **Bash tool** is often the most powerful tool for an agent. Instead of building custom tools for every action (e.g., a specific API wrapper for a file conversion), giving the agent access to the shell allows it to use existing software (like `ffmpeg`, `grep`, or `git`) to solve problems flexibly, similar to how a human developer works. * **Context Engineering:** Shihipar introduces the concept of **Context Engineering** via the file system. Instead of just "Prompt Engineering," the agent uses the file system to manage its state and context. * **Files as Memory:** The agent can write to files to "remember" things or create its own documentation (e.g., `CLAUDE.md`) to ground future actions. * **Verification:** The file system serves as a ground truth for the agent to verify its work (e.g., checking if a file was actually created). * **The Agent Loop & Intuition:** Building a successful agent loop is described as *"kind of an art or intuition"*. The loop generally follows a **Gather Context Take Action Verify Work** cycle. Shihipar emphasizes that this loop allows the agent to self-correct, a capability missing from rigid workflows. * **Strategies for Determinism (Hooks):** During the Q&A, a technique for controlling agent behavior is discussed: **Hooks**. * If an agent hallucinates or skips a step (e.g., guessing a Pokemon stat instead of checking a script), a hook can intercept the response and inject feedback: *"Please make sure you write a script, please make sure you read this data."* * This enforces rules like "read before you write" without retraining the model. * **Scaling to Large Codebases:** For massive codebases (50M+ lines), standard tools like `grep` or basic context window stuffing fail. * **Semantic Search Limitations:** Shihipar notes that while semantic search is a common solution, it is *"brittle"* because the model isn't trained on the specific semantic index. * **Solution:** He recommends good **"Claude MD"** files (context files) and starting the agent in a specific subdirectory to limit scope, rather than trying to index the entire 50M lines at once.