Hermes Agent¶
Information
Hermes Agent is an open-source autonomous AI agent developed by Nous Research and released in February 2026. Unlike standard chatbots or IDE plugins, this is a self-hosted solution that runs on your own server or computer, constantly learning and adapting to your tasks. Hermes Agent is ideal for developers, AI researchers, and automation enthusiasts who need a powerful, private, and flexible AI assistant.
Hermes Agent. Main Features¶
- Persistent Memory: The agent remembers your preferences, projects, and environment context between sessions. The longer it operates, the better it understands your needs, eliminating the need to re-explain context every time.
- Automated Skill Creation: Hermes features a built-in learning loop: while solving complex tasks, it automatically creates documents with reusable skills so it doesn't forget how to perform them in the future. These skills are compatible with the agentskills.io open standard.
- Multi-platform Gateway: You can interact with the agent through a single gateway via Telegram, Discord, Slack, WhatsApp, Signal, or directly from the Command Line Interface (CLI).
- Full Privacy and Independence: This is a 100% self-hosted solution. All data is stored locally on your machine (in the
~/.hermes/folder), telemetry and data collection are completely absent, and the code is open for independent audit under the MIT license. - Task Scheduler and Parallelism: The built-in cron scheduler allows you to configure automatic execution of routine tasks (e.g., daily reports or backups) with results sent to any messenger. Additionally, the agent can launch isolated sub-agents for parallel processing of multi-stage tasks without losing context. hermesagent.agency
- Research and Fine-tuning Tools (MLOps): Hermes Agent is positioned not only as an automation tool but also as a platform for generating training data. It supports batch processing, integration with the Atropos framework for Reinforcement Learning (RL), and exporting dialogue trajectories in ShareGPT format for fine-tuning language models.
Deployment Features¶
| ID | Software Name | OS | VPS | BM | VGPU | GPU | Min. CPU (Cores) | Min. RAM (GB) | Min. HDD/SSD (GB) | Custom Domain | Available |
|---|---|---|---|---|---|---|---|---|---|---|---|
Information
Deployment details for this software can be found at this link.
Note
Unless otherwise specified, we install the latest release version of the software from the developer's website or the operating system repositories by default.
Getting Started After Deploying Hermes Agent¶
After payment, a notification regarding the server's readiness will be sent to the email address provided during registration. It will contain the VPS IP address, as well as the login and password for connection. Customers manage their hardware in the server control panel and API — Invapi.
Authorization credentials can be found in the sent email:
- Login:
root; - Password: sent to your email address upon server delivery;
Connection and Initial Setup¶
After receiving server access, you must establish an SSH connection with root privileges:
Then, execute the following command: After running the command, the Interactive Setup Wizard will launch. Follow the wizard's prompts to connect the required model.
You can now begin working with Hermes Agent by launching it with the command:
Note
Detailed information on the main Hermes Agent settings is available in the developer documentation.
Ordering a Server with Hermes Agent via API¶
To install this software using the API, follow these instructions.