hermes-agent
The agent that grows with you
Hermes Agent is a self-improving AI agent framework from Nous Research that features a built-in learning loop, autonomous skill creation, and cross-session memory. It runs on diverse infrastructure—from local machines to serverless platforms—and integrates with messaging platforms like Telegram, Discord, and Slack. Developers can use any LLM provider (OpenAI, Anthropic, OpenRouter, or self-hosted models) and extend capabilities through MCP server integration, scheduled automations, and parallel subagent delegation.
Key Features
Use Cases
- 01Running a persistent AI assistant on a remote VPS or cloud VM accessible via Telegram or Discord from any device
- 02Automating scheduled tasks like daily reports, nightly backups, or weekly audits with delivery to messaging platforms
- 03Building custom AI workflows that learn and improve skills autonomously from completed multi-step tasks
- 04Developing research pipelines with batch trajectory generation for training next-generation tool-calling models
- 05Creating cross-session AI interactions that remember user preferences and context across days or weeks
- 06Extending agent capabilities by connecting MCP servers for specialized integrations like desktop control or domain-specific APIs
Related MCP Servers
View morepublic-apis
A collective list of free APIs
awesome-python
The definitive list that answers "I want to do X in Python, which tool should I use?"
awesome-selfhosted
A list of Free Software network services and web applications which can be hosted on your own servers
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
hermes-agent — FAQ
What is Hermes Agent MCP server?+
Hermes Agent is a self-improving AI agent framework that supports the MCP protocol, allowing it to connect external MCP servers for extended capabilities. It features autonomous skill learning, persistent memory, and multi-platform messaging integration.
How do I install Hermes Agent?+
On Linux, macOS, or WSL2, run: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash. On Windows PowerShell: iex (irm https://hermes-agent.nousresearch.com/install.ps1). After installation, run 'hermes setup' to configure your LLM provider and preferences.
Which AI clients and platforms work with Hermes Agent?+
Hermes Agent works with any LLM provider including OpenAI, Anthropic, OpenRouter, Nous Portal, and custom endpoints. It also connects to messaging platforms (Telegram, Discord, Slack, WhatsApp, Signal) and supports MCP server integration for extended tool capabilities.
Do I need API keys to use Hermes Agent?+
You need an API key for your chosen LLM provider (OpenAI, Anthropic, etc.) or a Nous Portal subscription. Optional API keys for tools like web search, image generation, or TTS can be provided individually or accessed through Nous Portal's Tool Gateway under one subscription.
Is Hermes Agent free and open source?+
Yes, Hermes Agent is released under the MIT license and is completely free and open source. You only pay for the LLM API costs from your chosen provider or optional Nous Portal subscription for unified access to models and tools.
Can Hermes Agent run on serverless infrastructure?+
Yes, Hermes Agent supports serverless deployment on Modal and Daytona with hibernation-based persistence. The agent environment automatically sleeps when idle and wakes on demand, significantly reducing costs between sessions while maintaining state.
How do I install hermes-agent?+
Open the source repository on GitHub and follow its README. hermes-agent is a mcp server — MCP Agents Market links you directly to the official repo.
Is hermes-agent free?+
hermes-agent is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.