Hermes Agent: Build a Self-Improving AI Agent

<div>Hermes Agent: Build a Self-Improving Open-Source AI Agent</div><div><br></div><div>Hermes is an open-source AI agent that grows with you.</div><div><br></div><div>Similar in spirit to OpenClaw, it can run on your computer or server, use tools, execute commands, automate workflows, manage memory, connect to external apps, and work with systems like Telegram, MCP, Ollama, Supabase, GitHub, Claude Code, Codex, ComfyUI, Obsidian, and more.</div><div><br></div><div>In this course, you will learn how to install Hermes, configure it, extend it with skills, connect it to tools, automate real workflows, and build self-improving agent systems that can support you in research, coding, productivity, content creation, and personal automation.</div><div><br></div><div>This is not a course about simple prompting tricks.</div><div><br></div><div>It is a practical, project-based course for people who want to understand how modern AI agents actually work — including tools, skills, memory, permissions, plugins, hooks, MCP servers, local models, subagents, scheduled tasks, and security.</div><div><br></div><div>What You Will Build and Learn</div><div><br></div><div>The course starts from zero.</div><div><br></div><div>First, you will learn what Hermes Agent is, how the harness works, how the architecture is structured, and why Hermes is different from a normal chatbot.</div><div><br></div><div>Then you will install Hermes in different ways:</div><div><ul><li><span style="font-size: 1rem;">locally on Mac, Linux, or Windows with WSL2</span></li><li><span style="font-size: 1rem;">on a VPS server</span></li><li><span style="font-size: 1rem;">inside a Docker container</span></li><li><span style="font-size: 1rem;">on a separate device or sandbox environment</span></li></ul></div><div><span style="font-size: 1rem;">You will configure LLMs, connect Telegram, use the Hermes dashboard, switch models, run basic commands, and understand how to work with Hermes in a real setup.</span></div><div><br></div><div><span style="font-size: 1rem;">Hermes Agent Foundations</span></div><div><br></div><div>You will learn the core concepts behind Hermes Agent:</div><div><ul><li><span style="font-size: 1rem;">installation options and setup workflows</span></li><li><span style="font-size: 1rem;">VPS setup with Docker</span></li><li><span style="font-size: 1rem;">Windows setup with WSL2 Ubuntu</span></li><li><span style="font-size: 1rem;">local installation on Mac, Linux, and Windows</span></li><li><span style="font-size: 1rem;">basic Hermes commands</span></li><li><span style="font-size: 1rem;">model switching</span></li><li><span style="font-size: 1rem;">dashboard usage</span></li><li><span style="font-size: 1rem;">documentation structure</span></li><li><span style="font-size: 1rem;">the Hermes harness and agent architecture</span></li></ul></div><div><span style="font-size: 1rem;">By the end of this part, you will have Hermes running and understand how the system is built.</span></div><div><br></div><div>Practical Hermes Workflows</div><div><br></div><div>After the setup, you will move into real usage.</div><div><br></div><div>You will test Hermes with browser automation, manage files on a VPS with VS Code and SSH, onboard your agent, work with the user file, manage memory, customize personality with soul file, and use context management to save tokens.</div><div><br></div><div>You will also learn:</div><div><ul><li><span style="font-size: 1rem;">how Hermes uses tools</span></li><li><span style="font-size: 1rem;">how skills work</span></li><li><span style="font-size: 1rem;">how to manage permissions</span></li><li><span style="font-size: 1rem;">how slash commands work</span></li><li><span style="font-size: 1rem;">how to run scheduled tasks with cron jobs</span></li><li><span style="font-size: 1rem;">how to enable voice input and output</span></li><li><span style="font-size: 1rem;">how to use Hermes as a more personal AI assistant</span></li><li><span style="font-size: 1rem;">This turns Hermes from a terminal-based AI tool into a practical agent you can actually use.</span></li></ul></div><div><span style="font-size: 1rem;">Advanced Hermes Agent Systems</span></div><div><br></div><div>The course then moves into more advanced agent workflows.</div><div><br></div><div>You will learn how to create your own Hermes skills, build self-improving skills, automate ComfyUI workflows, connect MCP servers, work with Supabase and SQL, bundle tools with plugins, use hooks for automation and logging, and integrate command-line tools like the GitHub CLI.</div><div><br></div><div>You will also explore reinforcement learning workflows, LoRA creation, and more advanced ways to extend Hermes beyond the default setup.</div><div><br></div><div>Topics include:</div><div><ul><li><span style="font-size: 1rem;">custom Hermes skills</span></li><li><span style="font-size: 1rem;">self-improving skills</span></li><li><span style="font-size: 1rem;">ComfyUI automation</span></li><li><span style="font-size: 1rem;">MCP server integration</span></li><li><span style="font-size: 1rem;">Supabase and SQL</span></li><li><span style="font-size: 1rem;">plugins</span></li><li><span style="font-size: 1rem;">hooks</span></li><li><span style="font-size: 1rem;">CLI integrations</span></li><li><span style="font-size: 1rem;">GitHub CLI</span></li><li><span style="font-size: 1rem;">reinforcement learning</span></li><li><span style="font-size: 1rem;">LoRA creation</span></li></ul></div><div><span style="font-size: 1rem;">Hermes Pro Workflows and Real Use Cases</span></div><div><br></div><div>In the pro section, you will see how Hermes can be used in more complex workflows.</div><div><br></div><div>You will explore use cases for fitness and nutrition, email and calendar management, smart home control, video editing, coding, repo monitoring, subagents, multi-agent delegation, Kanban boards, Obsidian, RAG-style knowledge systems, local models with Ollama, and automation through Zapier MCP.</div><div><br></div><div>You will learn how Hermes can connect to larger AI systems and work together with tools like Claude Code, Codex, Claude Design, Obsidian, Ollama, and MCP servers.</div><div><br></div><div>Use cases include:</div><div><ul><li><span style="font-size: 1rem;">Hermes as a personal assistant</span></li><li><span style="font-size: 1rem;">Hermes for video editing workflows</span></li><li><span style="font-size: 1rem;">Hermes for email and calendar automation</span></li><li><span style="font-size: 1rem;">Hermes with Zapier MCP and thousands of apps</span></li><li><span style="font-size: 1rem;">Hermes as a smart home assistant</span></li><li><span style="font-size: 1rem;">Hermes for coding and repo monitoring</span></li><li><span style="font-size: 1rem;">Hermes with Claude Code, Codex, and Claude Design</span></li><li><span style="font-size: 1rem;">subagents and multi-agent delegation</span></li><li><span style="font-size: 1rem;">Kanban-based task management</span></li><li><span style="font-size: 1rem;">Obsidian and LLM wiki workflows</span></li><li><span style="font-size: 1rem;">RAG-style knowledge databases</span></li><li><span style="font-size: 1rem;">local models with Ollama</span></li></ul></div><div><span style="font-size: 1rem;">AI Agent Security</span></div><div><br></div><div>Powerful AI agents are useful, but they also introduce new risks.</div><div><br></div><div>That is why the final section covers important security topics for AI agents, including jailbreaks, prompt injections, tool poisoning, MCP rug pulls, hidden instructions, unsafe permissions, and the risks of giving agents access to files, APIs, terminals, tools, and external systems.</div><div><br></div><div>You will learn what can go wrong, what to watch out for, and how to think more carefully when building and using agentic systems.</div><div><br></div><div>By the End of This Course</div><div><br></div><div>By the end of the course, you will understand how to install Hermes Agent, configure it, connect it to tools, customize its memory and personality, build your own skills, automate tasks, work with MCP servers, use plugins and hooks, run scheduled jobs, connect external apps, use local models, delegate work to subagents, and think more clearly about AI agent security.</div><div><br></div><div>Hermes Agent should no longer feel like a mysterious open-source project.</div><div><br></div><div>It should feel like a practical AI agent system you can run, control, extend, and use for real work.</div><div><br></div><div>If you want to stop using AI only as a chatbot and start building your own open-source AI agent workflows with Hermes Agent, this course gives you the practical roadmap.</div>

What you'll learn:

• Learn how to install, run, customize, extend, and use Hermes Agent in real AI agent workflows
• Hermes Agent Foundations: Understand what Hermes Agent is, how the harness architecture works, and why it matters for open-source AI agents
• Installation & Setup: Install Hermes locally, on a VPS, in Docker, or on Windows with WSL2 Ubuntu
• LLM & Telegram Setup: Configure language models, connect Telegram, and prepare Hermes for real remote-control workflows
• Hermes Commands & Dashboard: Use basic Hermes commands, switch models, manage sessions, and work with the Hermes dashboard
• Browser Automation: Test Hermes with tools and browser automation to understand how agents interact with external systems
• Agent Onboarding: Configure your agent with user file and teach Hermes important context about you, your work, and your workflows
• Memory & Personality: Manage user file, memory, and soul file to create a more personalized AI assistant
• Context Management: Save tokens, manage sessions, and understand how Hermes handles context in longer workflows
• Skills System: Understand how Hermes skills work and how they allow your agent to perform reusable tasks
• Custom Hermes Skills: Build your own skills and extend Hermes with custom capabilities
• Self-Improving Skills: Create Hermes skills that can improve over time through research, feedback, and iteration
• Slash Commands & Permissions: Use Hermes slash commands, reasoning options, and permissions safely in real projects
• Cron Jobs & Scheduled Tasks: Automate recurring work with Hermes using cron jobs and scheduled agent workflows
• Voice Mode: Enable speech input and output to interact with Hermes through voice with Elevenlabs
• Manage server files with VS Code and SSH while working with Hermes on a remote machine
• MCP Integration: Connect Hermes Agent to external tools and systems using the Model Context Protocol
• Supabase & SQL Workflows: Build an MCP server example with Supabase and SQL for database-connected agent workflows
• Plugins: Bundle skills, tools, hooks, and CLIs into reusable Hermes plugins
• Hooks & Logging: Use hooks to automate workflows, trigger actions, and create better logging for your agent
• CLI Integration: Connect Hermes to command-line tools like the GitHub CLI for more powerful developer workflows
• ComfyUI Automation: Use Hermes skills to automate and manage ComfyUI workflows
• RL Training & LoRA Creation: Understand how Hermes can be used in reinforcement learning workflows and LoRA creation
• Subagents & Parallel Agents: Use subagents, multi-agent delegation, and parallel agent workflows for more complex tasks
• Kanban-Based Agent Workflows: Organize and delegate work with Kanban boards and agent task management
• Hermes for Coding: Monitor repositories, delegate coding tasks, and connect Hermes with Claude Code, Codex, and Claude Design
• Hermes for Video Editing: See how Hermes can support video editing workflows, including how an agent helped edit this course
• Email & Calendar Automation: Manage emails, calendar workflows, and thousands of apps using the Zapier MCP
• Smart Home Automation: Use Hermes as a smart home assistant to control devices, cameras, and automations
• Obsidian & LLM Wiki: Build knowledge workflows with Obsidian, Claude Code, Hermes Agent, and RAG-style databases
• Local Models with Ollama: Connect Hermes to local models using Ollama for more private and flexible AI workflows
• Real AI Agent Use Cases: Apply Hermes to fitness, nutrition, research, coding, automation, personal assistance, and creative workflows
• AI Agent Security: Understand jailbreaks, prompt injections, tool poisoning, MCP rug pulls, and hidden risks in agentic systems
• Permissions & Safe Usage: Learn how to think about safety when giving AI agents access to files, tools, APIs, terminals, and external systems
• OpenClaw-Style Agent Workflows: Build and run Hermes workflows similar in spirit to OpenClaw, but with your own setup and tools