Skip to content
Hermes Agent Module - Now on Fluent

Deploy Your Own Self-Improving AI Agent

Hermes Agent is the new self-hosted AI from Nous Research: an autonomous agent that lives on your server, remembers what it learns, and gets more capable the longer it runs. This is the complete setup, configuration, and operations guide.

Built by Nous Research · 6 messaging channels

What Does Hermes Agent Actually Do?

Hermes is an autonomous agent process running on your server. You send messages from any app you already use. Hermes picks the right model, executes the work (web search, browser automation, code, file ops, scheduled jobs) and replies. Then it remembers what it learned, generates a reusable skill if it solved something complex, and gets a little better next time.

You (Telegram): "Pull the top 5 LLM reasoning papers from this week and summarize the takeaways"

→ Hermes routes: GLM-4.6 via Nous Portal (long context, low cost)

→ Skill triggers: web_search + page_browse + summarize

→ Auto-curated: stores user preference for paper discovery format

Hermes: "Here are the 5 papers, ranked by citation velocity..."

Total time: 8s · Cost: $0.012 · Skill saved for next time

Why Self-Host?

Commercial AI assistants charge per-seat subscriptions, log every conversation, and lock you to one model family. Self-hosting Hermes flips the equation: you pay for compute, your conversations stay on your hardware, and you can swap models with one command.

Hermes (self-hosted)Commercial assistants
Cost$5-30/mo VPS + usage-based model$20-100/mo per seat
Privacy100% on your infrastructureConversations logged by provider
ModelsNous Portal, OpenRouter (200+), OpenAI, Anthropic, GLM, Kimi, MiniMax, customProvider's choice, single family
ChannelsTelegram, Discord, Slack, WhatsApp, Signal, Email, CLIDepends on plan
MemoryPersistent, auto-curated, cross-sessionLimited or session-scoped
SkillsAuto-generated from your work, agentskills.io compatibleNone
SandboxingLocal, Docker, SSH, Daytona, Singularity, ModalProvider-managed
Always-onYes, VPS or serverless hibernationYes

What You Get

Eight features that distinguish Hermes from a chat wrapper or a coding copilot. All open source, MIT licensed, fully under your control.

One Agent, Every Channel

A single gateway exposes Hermes through Telegram, Discord, Slack, WhatsApp, Signal, Email, and CLI. Voice memo transcription, cross-platform conversation continuity, per-platform access control.

A Closed Learning Loop

Auto-curated memory between turns. New skills generated after solving complex tasks, then improved as they're used. Full-text search over past sessions with LLM summarization for cross-session recall.

Use Any Model

Switch between Nous Portal, OpenRouter (200+), OpenAI, Anthropic, GLM, Kimi, MiniMax, or your own endpoint with one command. No code changes, no lock-in.

Real Sandboxing

Six terminal backends (local, Docker, SSH, Daytona, Singularity, Modal) with container hardening and namespace isolation. Daytona and Modal hibernate when idle, costing nearly nothing between sessions.

Scheduled Automations

Built-in cron scheduler with delivery to any channel. "Send me a Telegram summary of GitHub issues every Monday at 9am": natural language in, scheduled task out, running unattended.

Delegates and Parallelizes

Spawn isolated subagents for parallel workstreams, each with its own conversation, terminal, and Python RPC scripts. Collapse multi-step pipelines into zero-context-cost turns.

MCP Native

Connect any MCP server for extended capabilities. Use the same Model Context Protocol stack you've been building with Claude Code, on a different runtime, on your own infrastructure.

You Own Everything

Conversations stay on your hardware. Skills, memory, and config live in ~/.hermes. API keys stay in your .env. No telemetry by default. Full control, full audit trail.

Coming From OpenClaw?

If you already have OpenClaw running, Hermes ships with a built-in migration command. Persona, memories, custom skills, command allowlist, messaging configs, and API keys imported in one shot, with a dry-run preview before anything changes.

One command. Your existing setup, on Hermes.

Imports SOUL.md, MEMORY.md and USER.md, your custom skills (into ~/.hermes/skills/openclaw-imports/), command approval patterns, platform configs, and allowlisted API keys.

Compare both modules →
$hermes claw migrate --dry-run

The Full Module - 8 Lessons

From first install to a hardened, self-improving agent running across every channel. Lesson 1 is free.

01
What Is Hermes Agent?Free

Architecture overview, the learning loop, how it compares to OpenClaw and Claude Code.

Start →
02
Install & First Conversation

Linux, macOS, or WSL2 in under five minutes. Pick a model, run hermes, ship your first task.

Pro
03
Configure the Messaging Gateway

Telegram, Discord, Slack, WhatsApp, Signal, Email: full setup with access control and per-platform personas.

Pro
04
Models, Routing, Cost Control

Nous Portal, OpenRouter, GLM, Kimi, OpenAI, Anthropic. Routing strategies, fallback chains, monthly budget tracking.

Pro
05
Skills, Memory, the Learning Loop

How auto-curation works, when to write skills manually, working with the Skills Hub, and what not to put in memory.

Pro
06
Sandboxing & Subagents

Pick the right terminal backend (local vs Docker vs Modal vs Daytona). Spawn parallel subagents for long-running pipelines.

Pro
07
Cron, MCP, Production Ops

Scheduled tasks, MCP server integration, monitoring, backups, incident response.

Pro
08
Migration & Security Hardening

Full hermes claw migrate walkthrough. DM pairing, command approval policies, container isolation, monthly checklist.

Pro

Optional - Add a Web UI

Prefer a browser to a terminal? The community-built Hermes WebUI gives you near-1:1 parity with the CLI in a clean three-panel interface. No build step, no framework, vanilla JS.

Community Project

hermes-webui by @nesquena

Three-panel layout: sessions, chat, workspace files. Reachable through an SSH tunnel into your VPS, so you keep the same security posture with a friendlier surface. We cover the install in the Pro module. github.com/nesquena/hermes-webui ↗

Ready to deploy your own self-improving agent?

Start with the free lesson, no signup required. Upgrade to Pro when you're ready for the full setup, model routing, and production ops walkthroughs.

Part of the Fluent course