Hermes Desktop vs ServerEngine

Hermes Desktop gives you one self-improving agent in a window of its own, pointed at any model you like. ServerEngine gives you a workspace of agents on your own Windows machine, with the approvals, the scopes and the skills already built in.

Hermes Desktop

The Agent Workspace in ServerEngine: four agent panels in a grid work on their own jobs at the same time - a landing page, generative art, an analytics dashboard and an ROI calculator - each keeping its own checklist, editing files with the new lines shown as green diffs and checking its own work in a headless browser, while one of them takes a spoken follow-up asking for higher quality.

Feature by feature

	Hermes Desktop	ServerEngine
Models	Provider-agnostic: Nous Portal, OpenRouter, Anthropic, OpenAI, Google, xAI and any OpenAI-compatible endpoint.	Claude Code, Codex CLI, Grok Build, OpenRouter and local Ollama, chosen per agent.
Your existing subscription	Signs in to Nous Portal, Codex, Copilot or Anthropic by OAuth, or takes an API key.	Runs on the Claude, ChatGPT or Grok subscription you already have, or your own OpenRouter key. One provider runs dry, switch the agent to another.
Getting started	An installer for macOS, Windows and Linux that puts the agent core and its runtime on the machine, and updates itself from inside the app.	A signed app from the Microsoft Store. Nothing to install underneath it, and it updates itself.
Agent Workspace	A chat-first window with a sidebar: several conversations at once, and profiles that appear as bots with their own memory and skills.	A grid of agents working side by side, each with its own task, model and folder. Every session is saved and restored on startup.
Talk or type	Talk to it and hear it back, in the app.	Speak your prompt with local speech-to-text, and hear the answer once the task is done.
Memory	Memory that carries between sessions, skills it writes for itself, and a memory graph you can open and edit in place.	One memory shared by every model, filed per work folder, growing into a neuron you can open and manage in the chat.
From your phone	A messaging gateway for Telegram, Discord, Slack, WhatsApp, Signal and a long list of others.	Slack and Discord reach the agents in your workspace, one channel per agent. WhatsApp reaches the main chat, approvals included.
Agents on a schedule	Recurring routines backed by cron.	Any prompt on a timetable, each with its own model, reasoning effort and allowed skills, and a live transcript while it runs.
Plans you can follow	Tools can be set to ask before they run. A plan you approve before the work starts is not among the announced features.	Plan mode proposes the work first, then ticks each step off a checklist you watch. You decide skill by skill what has to ask first.
Code editing	File and terminal tools, with a projects view that follows the agent as it reads and writes.	The fastest code editor for agents: built in pure C++, with batched calls so edits land in a fraction of the time.
Built-in skills	An open skills catalogue, skills it writes for itself, and MCP servers.	Code, browser, computer use, image generation, GitHub, Cloudflare, Stripe, Jira and more, each switched on individually.
Work on your servers	The machine the app runs on, or a remote gateway you set up and keep running yourself.	On the Commander plan the agent also works on the servers in your network or a VPS in the cloud, inside scopes you approve.
Keep it local	Runs on your own hardware, and points at a local model if you give it one.	Runs on your own Windows machine. With an Ollama model, nothing leaves your network.

Models

Hermes Desktop

Provider-agnostic: Nous Portal, OpenRouter, Anthropic, OpenAI, Google, xAI and any OpenAI-compatible endpoint.

ServerEngine

Claude Code, Codex CLI, Grok Build, OpenRouter and local Ollama, chosen per agent.

Your existing subscription

Hermes Desktop

Signs in to Nous Portal, Codex, Copilot or Anthropic by OAuth, or takes an API key.

ServerEngine

Runs on the Claude, ChatGPT or Grok subscription you already have, or your own OpenRouter key. One provider runs dry, switch the agent to another.

Getting started

Hermes Desktop

An installer for macOS, Windows and Linux that puts the agent core and its runtime on the machine, and updates itself from inside the app.

ServerEngine

A signed app from the Microsoft Store. Nothing to install underneath it, and it updates itself.

Agent Workspace

Hermes Desktop

A chat-first window with a sidebar: several conversations at once, and profiles that appear as bots with their own memory and skills.

ServerEngine

A grid of agents working side by side, each with its own task, model and folder. Every session is saved and restored on startup.

Talk or type

Hermes Desktop

Talk to it and hear it back, in the app.

ServerEngine

Speak your prompt with local speech-to-text, and hear the answer once the task is done.

Memory

Hermes Desktop

Memory that carries between sessions, skills it writes for itself, and a memory graph you can open and edit in place.

ServerEngine

One memory shared by every model, filed per work folder, growing into a neuron you can open and manage in the chat.

From your phone

Hermes Desktop

A messaging gateway for Telegram, Discord, Slack, WhatsApp, Signal and a long list of others.

ServerEngine

Slack and Discord reach the agents in your workspace, one channel per agent. WhatsApp reaches the main chat, approvals included.

Agents on a schedule

Hermes Desktop

Recurring routines backed by cron.

ServerEngine

Any prompt on a timetable, each with its own model, reasoning effort and allowed skills, and a live transcript while it runs.

Plans you can follow

Hermes Desktop

Tools can be set to ask before they run. A plan you approve before the work starts is not among the announced features.

ServerEngine

Plan mode proposes the work first, then ticks each step off a checklist you watch. You decide skill by skill what has to ask first.

Code editing

Hermes Desktop

File and terminal tools, with a projects view that follows the agent as it reads and writes.

ServerEngine

The fastest code editor for agents: built in pure C++, with batched calls so edits land in a fraction of the time.

Built-in skills

Hermes Desktop

An open skills catalogue, skills it writes for itself, and MCP servers.

ServerEngine

Code, browser, computer use, image generation, GitHub, Cloudflare, Stripe, Jira and more, each switched on individually.

Work on your servers

Hermes Desktop

The machine the app runs on, or a remote gateway you set up and keep running yourself.

ServerEngine

On the Commander plan the agent also works on the servers in your network or a VPS in the cloud, inside scopes you approve.

Keep it local

Hermes Desktop

Runs on your own hardware, and points at a local model if you give it one.

ServerEngine

Runs on your own Windows machine. With an Ollama model, nothing leaves your network.

The best upgrade for your AI agents

Run many agents side by side. Every session is saved and restored on startup. Switch between Workspaces and use your favorite models from Claude Code, Codex CLI, Grok Build and OpenRouter while sharing the same memory system.

Integrates with Claude Code CLI
Integrates with Codex CLI
Integrates with Grok Build
Integrates with OpenRouter API
Integrates with Ollama App

Why type every prompt? Just talk.

Explaining a goal out loud is quicker than typing, and easier to get into detail. Speak your prompt and the agent answers back once the task is done.

Hey, I'm SENTRI. What can I help you with today?

Your agents get smarter over time

The agent learns and acts based on your conversations. Every memory is linked to a work folder. Memories grow into a neuron you can manage within the chat.

Tied to your desk? Not anymore.

Send a message from your phone. Your agents keep working while you enjoy some free time.

Two phones side by side showing the same Slack thread. On the left the agent is asked to build a landing page for a burger shop and deploy it to Cloudflare, and reports each step as it finishes. On the right it is told to use the Cloudflare skill and then to validate the page in a browser, which it does and confirms the site is live.

The fastest code editor for agents

Lightning-fast code edits. How? It's built in pure C++ and makes use of batch calls to significantly improve performance.

Plug in your integration

Bring your own model

ClaudeClaude Code · use your subscription

CodexCodex CLI · use your subscription

GrokGrok Build · use your subscription

OpenRouterSelf powered · use your API key

OllamaFully local · stays in your network

S.E.N.T.R.I

$24

billed monthly

The AI agent & Workspace

S.E.N.T.R.I Agent
Agentic Workspace
Multi-step task planning
Agents on a schedule
Agent skills & approvals
Coding agent integration
Local speech-to-text
Voice responses

Try now, pay later

Commander

$50

billed monthly

S.E.N.T.R.I + Server management & API.

Everything in S.E.N.T.R.I
Zero-trustSecretless authentication: the agent only knows the hostname. agent access
Agent Guardrails (ScopesScopes are approved host groups for S.E.N.T.R.I)
Remote Manager
Admin Console
RESTful API access

Subscribe in APP

Enterprise

Custom

Compliance-grade automation, priced to your needs.

Everything in Commander
Managed script automation
Integrated script editor
Create and save runbooks
Signed script execution
WinGet software deployment
User audit logs
Q.U.O. HR onboarding app
Priority support

Contact sales

The S.E.N.T.R.I plan is free for 7 days, then cancel anytime, with a 14-day money-back guarantee.

Plans are bought inside the app: install ServerEngine, open the License tab and pick your plan.

Ready when you are.

Get ServerEngine and pick your plan inside the app.

Get it on Microsoft Store

ISO 27001 aligned SOC 2 Type I aligned