Master Hermes Agent
The definitive learning community for Hermes Agent β the self-improving AI agent with 74.9k+ GitHub stars.
bash β hermes-setup
$curl -fsSL hermes.sh | bash
> Bootstrapping AI cognitive core...
> Hooking into Telegram & CLI...
> π Hermes Agent is active and ready.
Why Hermes Agent?
π§
Self-Learning Loop
Automatically creates skills from experience, improves them during use, and builds a deepening model of who you are.
π
Deploy Anywhere
Talk to it from Telegram, Discord, or CLI while it runs silently on a $5 VPS or Modal serverless infrastructure.
π
Multi-Agent Orchestration
Spawn isolated sub-agents for parallel workstreams. The host unifies scheduling natively and safely.
Latest Tutorials
View All βπ
π’ Beginnerβ± 8 min read
How to Install Hermes Agent: Complete Guide
Step-by-step installation guide for Linux, macOS, WSL2, and Android Termux.
installationsetup
π¬
π’ Beginnerβ± 6 min read
Your First Conversation with Hermes Agent
Learn how to effectively chat with your AI Agent, create sessions, and manage context.
beginnerchat
π€
π’ Beginnerβ± 10 min read
How to Choose the Right AI Model
Compare GPT-4o, Claude 3.5, Llama 3, and 200+ models to find your perfect fit.
modelsopenrouter
π±
π‘ Intermediateβ± 12 min read
Set Up Hermes Agent on Telegram
Deploy your AI Agent to Telegram for 24/7 mobile conversations.
telegrammessaging
FAQ
Hermes Agent is an open-source, self-improving AI agent built by Nous Research. It can learn from experience, create skills autonomously, and interact through Telegram, Discord, and CLI.
Hermes Agent itself is lightweight β it runs on any Linux server, macOS, WSL2, or even Android Termux. The AI model runs remotely via API (OpenRouter, OpenAI, etc.), so no GPU required.
Over 200 models including GPT-4, Claude, Llama, Mistral, and any OpenAI-compatible API. You can switch models on-the-fly.
Hermes can spawn isolated sub-agents for parallel tasks. Each sub-agent has its own context and can run independently while the host coordinates scheduling.
Yes. Hermes runs on your own infrastructure. Your conversations and data stay on your server. No data is sent to third parties except the AI model API you choose.