Skip to main content

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.

Fastest path to a working agent

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.

๐Ÿš€ InstallationInstall in 60 seconds on Linux, macOS, WSL2, or native Windows
๐Ÿ“– Quickstart TutorialYour first conversation and key features to try
๐Ÿ—บ๏ธ Learning PathFind the right docs for your experience level
โš™๏ธ ConfigurationConfig file, providers, models, and options
๐Ÿ’ฌ Messaging GatewaySet up Telegram, Discord, Slack, WhatsApp, Teams, or more
๐Ÿ”ง Tools & Toolsets60+ built-in tools and how to configure them
๐Ÿง  Memory SystemPersistent memory that grows across sessions
๐Ÿ“š Skills SystemProcedural memory the agent creates and reuses
๐Ÿ”Œ MCP IntegrationConnect to MCP servers, filter their tools, and extend Hermes safely
๐Ÿงญ Use MCP with HermesPractical MCP setup patterns, examples, and tutorials
๐ŸŽ™๏ธ Voice ModeReal-time voice interaction in CLI, Telegram, Discord, and Discord VC
๐Ÿ—ฃ๏ธ Use Voice Mode with HermesHands-on setup and usage patterns for Hermes voice workflows
๐ŸŽญ Personality & SOUL.mdDefine Hermes' default voice with a global SOUL.md
๐Ÿ“„ Context FilesProject context files that shape every conversation
๐Ÿ”’ SecurityCommand approval, authorization, container isolation
๐Ÿ’ก Tips & Best PracticesQuick wins to get the most out of Hermes
๐Ÿ—๏ธ ArchitectureHow it works under the hood
โ“ FAQ & TroubleshootingCommon 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_code collapses 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.txt โ€” curated index of every doc page with short descriptions. ~17 KB, safe to load into an LLM context.
  • /llms-full.txt โ€” 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.