Hermes Agent
The self-improving AI agent built by Nous Research. The only agent with a built-in learning loop โ it creates skills from experience, improves them during use, nudges itself to persist knowledge, and builds a deepening model of who you are across sessions.
Installโ
Windows or macOSโ
To easily install the command-line and desktop applications, download the Hermes Desktop installer from our website and run it.
Without Hermes Desktop:โ
For a command-line only install without Hermes Desktop, run:
Linux / macOS / WSL2 / Android (Termux)โ
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
Windows (native)โ
Run in powershell:
iex (irm https://hermes-agent.nousresearch.com/install.ps1)
See the full Installation Guide for what the installer does, the per-user vs root layout, and Windows-specific notes.
After installing, run hermes setup --portal โ one OAuth covers a model plus all four Tool Gateway tools (web search, image generation, TTS, browser). See Nous Portal.
What is Hermes Agent?โ
It's not a coding copilot tethered to an IDE or a chatbot wrapper around a single API. It's an autonomous agent that gets more capable the longer it runs. It lives wherever you put it โ a $5 VPS, a GPU cluster, or serverless infrastructure (Daytona, Modal) that costs nearly nothing when idle. Talk to it from Telegram while it works on a cloud VM you never SSH into yourself. It's not tied to your laptop.
Quick Linksโ
| ๐ Installation | Install in 60 seconds on Linux, macOS, WSL2, or native Windows |
| ๐ Quickstart Tutorial | Your first conversation and key features to try |
| ๐บ๏ธ Learning Path | Find the right docs for your experience level |
| โ๏ธ Configuration | Config file, providers, models, and options |
| ๐ฌ Messaging Gateway | Set up Telegram, Discord, Slack, WhatsApp, Teams, or more |
| ๐ง Tools & Toolsets | 60+ built-in tools and how to configure them |
| ๐ง Memory System | Persistent memory that grows across sessions |
| ๐ Skills System | Procedural memory the agent creates and reuses |
| ๐ MCP Integration | Connect to MCP servers, filter their tools, and extend Hermes safely |
| ๐งญ Use MCP with Hermes | Practical MCP setup patterns, examples, and tutorials |
| ๐๏ธ Voice Mode | Real-time voice interaction in CLI, Telegram, Discord, and Discord VC |
| ๐ฃ๏ธ Use Voice Mode with Hermes | Hands-on setup and usage patterns for Hermes voice workflows |
| ๐ญ Personality & SOUL.md | Define Hermes' default voice with a global SOUL.md |
| ๐ Context Files | Project context files that shape every conversation |
| ๐ Security | Command approval, authorization, container isolation |
| ๐ก Tips & Best Practices | Quick wins to get the most out of Hermes |
| ๐๏ธ Architecture | How it works under the hood |
| โ FAQ & Troubleshooting | Common questions and solutions |
Key Featuresโ
- A closed learning loop โ Agent-curated memory with periodic nudges, autonomous skill creation, skill self-improvement during use, FTS5 cross-session recall with LLM summarization, and Honcho dialectic user modeling
- Runs anywhere, not just your laptop โ 6 terminal backends: local, Docker, SSH, Daytona, Singularity, Modal. Daytona and Modal offer serverless persistence โ your environment hibernates when idle, costing nearly nothing
- Lives where you do โ CLI, Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Mattermost, Email, SMS, DingTalk, Feishu, WeCom, Weixin, QQ Bot, Yuanbao, BlueBubbles, Home Assistant, Microsoft Teams, Google Chat, and more โ 20+ platforms from one gateway
- Built by model trainers โ Created by Nous Research, the lab behind Hermes, Nomos, and Psyche. Works with Nous Portal, OpenRouter, OpenAI, or any endpoint
- Scheduled automations โ Built-in cron with delivery to any platform
- Delegates & parallelizes โ Spawn isolated subagents for parallel workstreams. Programmatic Tool Calling via
execute_codecollapses multi-step pipelines into single inference calls - Open standard skills โ Compatible with agentskills.io. Skills are portable, shareable, and community-contributed via the Skills Hub
- Full web control โ Search, extract, browse, vision, image generation, TTS โ one subscription via Nous Portal bundles all of them
- MCP support โ Connect to any MCP server for extended tool capabilities
- Research-ready โ Batch processing, trajectory export, RL training with Atropos. Built by Nous Research โ the lab behind Hermes, Nomos, and Psyche models
For LLMs and coding agentsโ
Machine-readable entry points to this documentation:
/llms.txtโ curated index of every doc page with short descriptions. ~17 KB, safe to load into an LLM context./llms-full.txtโ every doc page concatenated into a single markdown file for one-shot ingestion. ~1.8 MB.
Both files also resolve at /docs/llms.txt and /docs/llms-full.txt. Generated fresh on every deploy.