25 Hermes Agent Use Cases (2026): Real Examples, Ideas and Setup Commands

These Hermes Agent use cases aren't hypothetical. Fifteen come from real users running Hermes in production. Ten come straight from Hermes's own release notes, so you can set them up today. Some are better served by Hermes. Some are better served by something else. Here's the honest list.

Updated November 2, 2026, for Hermes v0.22.5.

@EXM7777 posted this on April 30: "3 weeks ago I decided to setup a Hermes agent for my family (3 members), they all use it for different use cases, one $200 ChatGPT sub is more than enough. It opened a whole new world for them, just because it lives inside WhatsApp and has magic proactive behaviors."

A family of three sharing one AI agent on WhatsApp. Not a developer tool. Not an enterprise deployment. A family assistant. (If you're new to Hermes, our overview of what Hermes Agent is explains the learning loop and memory that make these always-on deployments work.)

That's the use case no one expected from Hermes. And it's one of 25 on this list.

Where these use cases come from

• Use cases 1 to 15 are user stories: real setups people documented on X, GitHub, community forums and the Nous Research user stories page.
• Use cases 16 to 25 come from Hermes's release notes and docs, from v0.14.0 in May to v0.22.0 in October. They're things the software now does out of the box.
• "More ideas from the community" at the end lists setups people have shared that we haven't verified ourselves.

What changed in this update: Hermes v0.22.0, "The Threshold Release", shipped on October 14, 2026, and patches followed up to v0.22.5 on October 23. It added hosted app connectors, one-click local models, a live "Bot Screen" you can take over, a 600-plugin catalog, and a desktop app that sets itself up on a free trial model. We added four use cases it makes possible (22 to 25) and updated use cases 2, 3, 6 and 20.

All Hermes Agent use cases at a glance

Setup effort is our estimate for someone who already has Hermes running.

Running Hermes for a whole team? Nous sells that as Hermes for Businesses. It's a product rather than something users have documented, so we cover it after use case 25.

Hermes Agent use cases by who you are

• Personal use cases: 7 (car), 8 (health data), 10 (inbox digest), 11 (family WhatsApp assistant), 12 (visual novel), 19 (voice assistant), 23 (private local assistant), 25 (smart home).
• Business use cases: 4 (content gaps), 5 (lead generation), 9 (price monitoring), 13 (video handoff), 15 (competitor intelligence), 17 (monitors with memory), 18 (parallel research), 21 (Teams meeting summaries), 22 (Notion and Linear), plus Hermes for Businesses.
• Developer use cases: 1 (Claude Code orchestrator), 2 (memory bridge), 3 (local model tuning), 6 (agent fleet), 14 (translation extension), 16 (named bots), 20 (credential vault), 24 (Bot Screen).

How to read the commands below

Every command and config key below is checked against the Hermes docs and the CLI source on the main branch of the NousResearch/hermes-agent repo, as of v0.22.5 on November 2, 2026. Where a use case has no dedicated command, we show the config or the in-chat instruction instead and say so. Text in angle brackets is a placeholder.

On models: every use case needs a model with tool calling and at least 64,000 tokens of context. Hermes rejects smaller windows at startup, and most hosted Claude, GPT, Gemini, Qwen and DeepSeek models clear that easily. Nous says every automation blueprint works with any model, so the "Model" line under each use case only flags where a use case needs something more. Run hermes model to add a provider, switch the default, or (since v0.22.0) see how much of your subscription is left before you hit a limit.

On a phone? Each use case starts with a plain-language line on what it does. The commands are there when you're back at a keyboard.

The Hermes Agent use cases

1. Claude Code orchestrator and reviewer

@luminousix built a bridge where Hermes writes prompts for Claude Code over SSH, reviews the output, and routes corrections back. "My Hermes agent is a Claude Code orchestrator and reviewer." One agent managing another.

What it does: Hermes hands coding tasks to Claude Code on another machine, then checks the work.

Config: Hermes ships a bundled claude-code skill that drives the Claude Code CLI in print mode (claude -p). To run it on a remote box, point Hermes's terminal at that machine over SSH:

# ~/.hermes/config.yaml: terminal: { backend: ssh }
# ~/.hermes/.env
TERMINAL_SSH_HOST=dev-box.example.com
TERMINAL_SSH_USER=ubuntu

Then ask in chat: "Use the claude-code skill to add error handling to src/api, then review the diff and send it back with corrections."

Model: any tool-calling model for Hermes itself. Claude Code runs on its own login, separately from Hermes's model.

2. Cross-agent memory bridge

@rohitg00 built a memory provider plugin that connects agent memory across Hermes, Claude Code and Cursor, with hybrid BM25 + vector + knowledge-graph search. Your coding agent and your messaging agent share one knowledge base.

What it does: your agents remember the same things, whichever one you're talking to.

Config: @rohitg00's plugin is community-built, so there's no official command for it. The documented route is Hermes's external memory slot, which takes one provider at a time on top of the built-in MEMORY.md and USER.md:

hermes memory setup   # pick a provider: retaindb, byterover, or a catalog plugin
hermes memory status  # confirm which provider is active

Since v0.22.0, most memory providers (Honcho, Supermemory, Hindsight, Mem0, OpenViking, Holographic) live in the plugin catalog, while ByteRover and RetainDB stay bundled. Existing setups were migrated automatically. Our Hermes memory providers guide compares them.

Model: no special requirement. The memory provider does the retrieval.

3. Local model inference tuning

@alexcovo_eth used Hermes TurboQuant skills to optimize Qwen3.5-9B-MLX on Apple Silicon. The agent applied, tested, documented and packaged the optimization path. A repeatable ML workflow managed by the agent itself.

What it does: Hermes runs, tests and tunes an AI model on your own computer.

The easy route (v0.22.0+): Hermes now installs and manages llama.cpp for you, with the right engine for your hardware (CPU, CUDA, Metal, Vulkan or ROCm). It rates every catalog model against your GPU and RAM and picks the best build that fits. Open Settings → Providers → Local Models in the desktop app, or run:

hermes model   # then choose "Local models"

The advanced route (MLX): to point Hermes at your own MLX server, as in the original setup:

model:
  provider: custom
  default: Qwen3.5-9B-mlx-lm-mxfp4
  base_url: http://127.0.0.1:8000/v1
  context_length: 65536

Model: a local model with at least a 64K context window. The local catalog includes Qwen3.8 27B and Qwen3.6 35B-A3B. If running models locally is your goal, our pick for the best free OpenClaw model covers the trade-offs across local options.

4. Content gap analysis (automated weekly)

MindStudio documented this: Hermes scraped a YouTube channel, compared recent uploads to industry news, and found five content gaps. Set as a cron job, it delivers a weekly report to Telegram with no manual work.

What it does: every Monday, you get a list of topics your competitors cover and you don't.

Command: a weekly cron job (9:00 every Monday) with the bundled youtube-content skill:

hermes cron create "0 9 * * 1" \
  "Compare the last 10 uploads on <channel URL> with this week's industry news and list 5 content gaps." \
  --skill youtube-content \
  --name "Weekly content gaps" \
  --deliver telegram

Model: any tool-calling model. The news half uses Hermes's web search tool, which defaults to Firecrawl. Our Hermes Telegram setup guide covers the delivery side.

5. Automated lead generation

Same MindStudio demo: "Scrape the internet for Northwest London plumbing businesses, find leads that don't have a website, return three qualified leads so I can pitch them an AI-built website." Hermes found the businesses, checked they had no website, and wrote a pitch angle for each. Running on a $0.24/hour CPU instance.

What it does: finds local businesses that need what you sell, and tells you how to pitch them.

In-chat instruction (no dedicated command; a plain prompt in any connected chat, such as Slack):

Search for plumbing businesses in Northwest London, keep only the ones with no website,
and give me three qualified leads with a one-line pitch angle for each.

Model: any hosted tool-calling model. With the model hosted elsewhere, the machine only runs Hermes, which is why a CPU instance is enough.

For how Hermes and OpenClaw approach automation differently, our comparison page covers the architecture.

6. 4-agent fleet on one laptop

@ones_07389 runs a 4-agent Hermes system 24/7 on a 32GB Ubuntu laptop, managed by systemd and a custom watchdog. Default agent (PM) on Feishu WebSocket. Dev, DevOps and content agents delegated via ACP. 5 MCP servers. 34 tools. A self-learning distillation cron at 04:30 daily. A production multi-agent setup on consumer hardware.

What it does: four specialist agents split the work, around the clock, on one machine.

Command: the setup above used ACP. Today the documented way to run named agents side by side is one profile per agent, with the kanban board to hand work between them and a service to keep it running:

hermes profile create dev
hermes profile create devops
hermes profile create content
hermes kanban create "Draft this week's release notes" --assignee content
hermes gateway install   # systemd (Linux) or launchd (macOS) service

Since v0.22.0, one gateway serves every profile on the machine, so a new profile's bots go live without a restart, and each profile still keeps its own credentials, cron jobs and sessions. Feishu runs over WebSocket with FEISHU_CONNECTION_MODE=websocket in ~/.hermes/.env. To contain the fleet, our Hermes Docker install guide covers the official image.

Model: each profile has its own config, so each agent can run a different model. A cheap model for content and a stronger one for dev is a common split.

7. Car remote start and EV monitoring

@gwyntel built a skill to remote start their car, check the EV battery level and monitor charging from Hermes, after noticing no one had published one yet. IoT meets AI agent.

What it does: "Start the car and tell me the battery level" from any chat.

Config: there's no official car skill, so this is a custom skill. Any folder under ~/.hermes/skills/ with a SKILL.md is picked up automatically, no registration needed:

---
name: car-remote
description: Remote start the car and report EV battery and charging status
version: 1.0.0
---

Save it as ~/.hermes/skills/smart-home/car-remote/SKILL.md, then add the steps that call your car maker's API below the frontmatter.

Model: any tool-calling model. The skill does the device work.

8. Health data sync

@wysie_ built a standalone tool designed to work with Hermes: connect HC Webhook (a Play Store app) and sync Health Connect data locally. The agent processes health metrics without sending personal data to cloud APIs.

What it does: your phone's health data flows to your agent, which flags anything unusual.

Command: @wysie_'s tool does its own sync. If you want Hermes itself to receive pushed data, the documented route is a webhook subscription (enable the webhook platform first with hermes gateway setup):

hermes webhook subscribe health-sync \
  --prompt "New Health Connect data: {__raw__}. Log it and flag anything unusual." \
  --deliver log \
  --description "Health Connect sync"

Model: a local model (use case 23 is the one-click way) if the point is keeping health data off cloud APIs. A hosted model would see the data.

9. Price monitoring with alerts

MindStudio tested this: Hermes monitored Autotrader listings and flagged mispriced supercars. Scheduled as a cron job, it delivers deal alerts to Telegram. The same setup works for competitor pricing, stock alerts or real estate listings.

What it does: you get a message when something you're watching drops below the market price.

Command: Hermes bundles a product-price-monitor skill. Run its setup once in chat (define the listing and the alert rule), then schedule the check. --continuity stops it re-alerting on the same listing (see use case 17):

hermes cron create "every 6h" \
  "Check my Autotrader watch and alert on any listing priced well under market." \
  --skill product-price-monitor \
  --continuity \
  --deliver telegram

Model: any tool-calling model. If a scheduled job stops firing, our Hermes cron troubleshooting guide covers the usual causes.

10. Daily inbox digest

Many users run this: Hermes summarizes email every morning, pulls out action items, and sends a clean briefing to WhatsApp or Telegram before you open your laptop. The most common Hermes cron job after the heartbeat.

What it does: one short message each morning with what needs you today.

Command: the bundled email-inbox-triage skill does the prioritizing and defaults to read and draft, never send or delete. Pair it with the google-workspace skill for Gmail:

hermes cron create "every 1d at 07:00" \
  "Triage the last 24 hours of email: urgent threads, action items, drafts for anything that needs a reply." \
  --skill email-inbox-triage \
  --skill google-workspace \
  --deliver whatsapp

Our Hermes Gmail triage guide covers the Gmail side step by step.

Model: any tool-calling model.

If you want the use case without running Hermes: the daily digest, inbox triage and messaging automations above are what BetterClaw runs as a managed service. Same Telegram, Slack and Discord delivery, no laptop running 24/7, no systemd, no watchdog. Plans start at $19 a month for Starter, and Pro is $49 for 5 agents. See pricing →

If it's Hermes itself rather than the use case that isn't working for you, our ranked list of Hermes Agent alternatives compares six options by how long each takes to get a working agent.

11. Family WhatsApp assistant

@EXM7777's setup: three family members sharing one Hermes agent on WhatsApp. It handles different requests for each person and has "magic proactive behaviors" that surface useful information before anyone asks. Cost: one ChatGPT subscription ($200/month for the model access). It lives inside WhatsApp, which is why non-technical family members actually use it.

What it does: one shared assistant your whole family can message like a person.

Command: pair WhatsApp, allow each family member's number (country code, no +), then install the gateway as a service:

hermes whatsapp   # mode selection and QR-code pairing
# then in ~/.hermes/.env:
# WHATSAPP_ALLOWED_USERS=15551234567,15557654321
hermes gateway install   # keep it running in the background

Model: @EXM7777 used a ChatGPT subscription. In Hermes that's hermes model → "ChatGPT or Codex Subscription", which signs in with ChatGPT and uses Codex models. Since v0.22.0 the model picker shows how much of the plan is left and when it resets. Our guide to using a Claude or ChatGPT subscription with Hermes covers the details and limits. Hermes now ships in 16 languages, which helps if your family doesn't all use English.

12. RenPy visual novel generator

@ExileAI_0: "It found ComfyUI, figured out how to generate images locally with LM Studio, then asked me to turn on the internet to install RenPy. About 10 minutes later there popped up a small but complete RenPy novel with 10 images and a little story." The agent found tools, installed software, generated assets and assembled a complete creative project on its own.

What it does: turns a one-line idea into a small finished game with pictures.

Command: the agent found ComfyUI by itself here. Hermes now has an official optional ComfyUI skill, so you can install it up front and then ask in chat:

hermes skills install official/creative/comfyui
# then in chat: "Make a short RenPy visual novel with 10 locally generated images."

Model: any tool-calling model. The images come from ComfyUI on your own machine, not from the LLM.

13. Video production handoff

@vicky_dyor gave Hermes a screen recording and asked for a setup tutorial. The agent produced a HeyGen video with her avatar and kept her preferences in memory for follow-up work.

What it does: screen recording in, finished presenter video out.

Command: Hermes's bundled and official optional skills don't include a HeyGen skill, so this one is an in-chat instruction to an agent that can reach HeyGen. The closest documented route is the official AI presenter video skill (script plus image to presenter video), which isn't HeyGen:

hermes skills install official/creative/ai-presenter-video

Model: any tool-calling model. The avatar video is rendered by HeyGen or the skill's own pipeline, not by the LLM.

14. Browser translation extension

@misswuhanliang built HermesAI Translator, an open-source browser extension for translation, reading help, text polishing and summaries, powered by the Hermes-4-70B model. A consumer product built on the Hermes ecosystem.

What it does: translation and rewriting on any web page, powered by your own agent.

Config: an extension like this can call the model directly. To put Hermes Agent itself behind a browser extension, turn on its OpenAI-compatible API server, which serves /v1/chat/completions on port 8642 once you run hermes gateway:

# ~/.hermes/.env
API_SERVER_ENABLED=true
API_SERVER_KEY=<long-random-key>
API_SERVER_CORS_ORIGINS=<your extension's origin>

Keep the CORS list narrow: the API server exposes Hermes's full toolset, including terminal commands.

Model: HermesAI Translator runs on Nous's Hermes-4-70B. Through the API server, any model you've configured works.

15. Competitor intelligence (scheduled)

Hermes scrapes competitor websites on a schedule and delivers a formatted report every Monday. MindStudio put it well: "The difference between a task you run once and a task that runs every week without you touching it is the difference between a tool and a system."

What it does: a Monday report on what your competitors changed last week.

Command: Hermes bundles a competitor-news-monitor skill. Freeze the watchlist once in chat, then schedule it:

hermes cron create "every monday 9am" \
  "Check <competitor list> for pricing changes, launches, funding and incidents." \
  --skill competitor-news-monitor \
  --continuity \
  --deliver slack

Swap --deliver slack for discord to post there instead. Our Slack and Discord setup guides cover connecting each one.

Model: any tool-calling model.

16. A team of named bots in one group chat

v0.21.0 ("Pantheon", August 31, 2026) built Bot Mode into the desktop app. Every agent profile gets a name and an avatar. You can create Discord-style group chats where several bots and you talk in one room, and @-mention any bot. The same release added hermes peer, which lets a bot message a bot on another machine. The release notes' example: ask your research bot to hand its findings to your coding bot and get the reply back where you can read it. It's the 4-agent fleet from use case 6, without the ACP plumbing.

What it does: a group chat where you and your specialist bots work together.

Command: a Bot is a Hermes profile, so create the bots from the CLI. Group chats themselves are made in the desktop app's Bots tab; there's no CLI command for them:

hermes profile create researcher --description "Reads sources, writes findings."
hermes profile create coder
hermes -p researcher chat   # the same agent as the Bot in the desktop app
hermes peer add spark --url http://spark.lan:8377 --key <API_SERVER_KEY>   # a bot on another machine

Model: each Bot has its own model, so the researcher and the coder can run different ones.

17. Monitors that remember what they already told you

Also in v0.21.0, cron jobs load and update persistent memory like any other agent. Continuity feeds each run its own previous output, so a price watcher (use case 9) or a news scout stops re-alerting on the same thing. Monitor-mode jobs skip the LLM entirely when nothing changed, and every job gets a durable notepad. In the release notes' words: "Your 9am briefing job now knows what it told you yesterday."

What it does: alerts only for new things, and quiet checks cost nothing.

Command:

hermes cron create "every 6h" "Scan for news" --continuity --deliver telegram
hermes cron edit <job_id> --continuity   # turn it on for an existing job

Model: any tool-calling model. Quiet monitor ticks make no LLM call at all.

18. Parallel research you can steer mid-flight

delegate_task grew in three steps. v0.17.0 added background subagents that don't block your chat. v0.18.0 added fan-out, where several subagents' results come back as one combined answer ("research these five competitors in parallel"). v0.21.0 made them steerable while they run: list the children, send one a course correction, or stop it early and keep the partial result. v0.22.0 brought the same live view to the desktop app. Use cases 4 and 15 become one fan-out job.

What it does: several researchers at once, and you can redirect any of them mid-task.

Config plus in-chat instruction: there's no CLI command; you ask in chat ("Research these five competitors in parallel and give me one comparison"). In the classic CLI, Ctrl+T opens the live roster where you can steer or stop a child; in the TUI it's /agents. To run the workers on a cheaper model:

delegation:
  model: "<cheaper-model>"   # every delegate_task child runs on this
  provider: "openrouter"     # optional: route children to a different provider

Model: a strong main model to plan and merge, and optionally a cheaper delegation.model for the workers. Children inherit the main model if you leave it unset.

19. A hands-free voice assistant

v0.20.0 (August 3, 2026) added streaming conversational voice with barge-in, so you can interrupt mid-sentence. It also added on-device wake words ("hey Hermes", or a phrase you choose), with no audio leaving your machine while it waits. You can send a voice note on WhatsApp, Feishu, DingTalk, LINE, QQ, Photon or Weixin and get a transcribed, spoken answer back. The family WhatsApp assistant (use case 11) no longer needs anyone to type.

What it does: talk to your agent like a smart speaker, or by voice note.

Config:

stt:
  provider: "local"   # free local transcription; or groq, openai, mistral, xai, elevenlabs
wake_word:
  enabled: true
  phrase: "hey hermes"

In the CLI, /voice on turns voice mode on; in Telegram and Discord, /voice on makes the bot answer voice messages with voice.

Model: any chat model. Speech-to-text and text-to-speech are separate providers, and local transcription costs nothing.

20. Errands that need a login, without handing over the password

v0.21.2 (September 11, 2026) added a password-blind credential vault, and v0.22.0 extended it to the browser agent. Hermes can sign in, pay and fill in addresses from 1Password, Bitwarden or its own encrypted vault without the model ever seeing the secret. Two-factor codes come from a saved authenticator key, or you type them into a small prompt that never enters the conversation. Card and address fills at checkout need your confirmation. Treat this as the riskiest item on the list: an agent that can pay can also pay for the wrong thing, so keep approvals on.

What it does: "Log into GitHub and download last month's invoice" works, and your password stays out of the chat.

Commands: you don't have to set anything up first. Ask Hermes to log into a site and it shows a masked prompt to save the login the first time. To add logins, cards or addresses ahead of time:

hermes vault add --kind login     # also: --kind payment, --kind address
hermes vault list                 # metadata only, never the values
hermes vault rm <handle>
hermes vault sources              # which password managers Hermes can see

To pick a password manager account or opt one out:

vault:
  onepassword:
    account: ""        # `op --account` shorthand; empty = default
  bitwarden:
    enabled: false     # opt out of a detected manager

Model: any model. The password is filled straight into the page and never reaches the model's context.

21. Meeting summaries posted into Microsoft Teams

v0.14.0 (May 16, 2026) shipped Teams end to end, including a meeting pipeline. It fetches transcripts through Microsoft Graph, summarizes them, and posts the summary into a Teams chat or channel. The catch is operational: Graph subscriptions expire within 72 hours, so you have to schedule hermes teams-pipeline maintain-subscriptions. Our Hermes Teams setup guide walks through it.

What it does: every meeting ends with a summary posted where your team already works.

Command: enable the pipeline plugin, check it, then renew subscriptions every 12 hours with a script-only cron job (the script just runs hermes teams-pipeline maintain-subscriptions and lives in ~/.hermes/scripts/):

hermes plugins enable teams_pipeline
hermes teams-pipeline validate
hermes cron create "0 */12 * * *" --name "teams-pipeline-maintain-subscriptions" \
  --no-agent --script maintain-teams-subscriptions.sh --deliver local

Model: any tool-calling model for the summaries. The renewal job runs no LLM at all.

22. Work inside Notion, Linear and your other apps

v0.22.0 added hosted app connectors. Ask Hermes to do something in an app such as Notion or Linear, sign in once in your browser, and the tools work in the same turn. You don't need a Nous account to start: the first time you use an app, Hermes creates a free connectors-only identity. You can connect several named accounts of one app, such as a work and a home Notion, and the desktop's new Connectors page lists your hosted apps and MCP servers together.

What it does: "Turn this chat into Linear tickets" or "Add these notes to my Notion" from any chat.

Command:

hermes connectors connect notion --alias work
hermes connectors list
hermes connectors accounts

Or just ask in chat and follow the sign-in link. /connectors manages them from inside a chat.

Model: any tool-calling model.

23. A private assistant that never leaves your machine

The same one-click local models from use case 3, aimed at everyone rather than ML developers. Hermes downloads the model, installs the right inference engine for your hardware and handles memory and context sizes for you. Nothing leaves your computer, and there's no account or API key. Pair it with local voice transcription (use case 19) and the health data sync (use case 8) for an assistant that keeps everything at home.

What it does: a capable assistant with zero data sent to any AI company.

Command: in the desktop app, Settings → Providers → Local Models. In a terminal:

hermes model   # choose "Local models", then pick a model that fits your hardware

Model: whatever fits your machine. Hermes rates each catalog model against your GPU and RAM and suggests the best one. Expect slower and less capable answers than top hosted models on modest hardware.

24. Watch your bot work, and take over at logins

v0.22.0 added Bot Screen. On a headless Linux gateway (a server, a cloud VM or Hermes Cloud), each bot gets its own desktop that Hermes Desktop streams live. When the bot hits a login, a 2FA prompt, a CAPTCHA or a payment step, you take the screen, finish that step yourself, and hand control back so it carries on with the session you just signed into. With a Docker, SSH or Singularity backend, the bot's screen, computer use and browser all run inside the sandbox, never on your host.

What it does: the bot does the boring web work; you step in for the one part that needs a human.

Command (on the Linux gateway host):

hermes computer-use screen install
hermes computer-use screen start
hermes computer-use screen status

Then open the bot in Hermes Desktop to watch or take over.

Model: a model that's good at computer use and browsing. This pairs naturally with the credential vault in use case 20.

25. Smart home control with Home Assistant

Home Assistant used to be built into Hermes; in v0.22.0 it moved to the official plugin catalog (existing users were migrated automatically). It gives Hermes tools to list devices, read their state and call services, and it can receive Home Assistant state changes as events. "Turn off the downstairs lights", "is the garage door open?", or a cron job that warns you when a freezer sensor goes warm.

What it does: control and monitor your home from any chat, and get told when something changes.

Command:

hermes plugins install homeassistant
# then in ~/.hermes/.env:
# HASS_URL=http://homeassistant.local:8123
# HASS_TOKEN=<long-lived access token>

Model: any tool-calling model. Home Assistant does the device work.

One more that's easy to miss: since v0.20.0, Hermes can push signed events (session activity, turn completions, tool events) to any HTTP endpoint you register. That turns "the agent finished" into a trigger for your CI, dashboards or home automation.

Team use case: Hermes for Businesses

This one is different from the 25 above. It isn't something users have documented, or a feature in the open-source release notes. It's Nous Research's paid team product, sold through the Nous Portal.

On October 7, 2026, Nous announced a $90 million raise from investors including NVIDIA, Samsung, Union Square Ventures and Menlo, reported at a $1.5 billion valuation, and said it "will build and deliver Hermes for Businesses". The Hermes Business page on the Nous Portal (the navigation also calls it "Hermes Teams") has a "Create your team" button but still shows no price.

What the page describes:

• One central team balance. "One central balance funds the team" instead of each person topping up their own account.
• Per-member spend caps. Members draw from that balance "with per-member spend caps you set", and owners and admins see every dollar in the portal.
• A shared team skill library. Skills any member builds are published to the team library and become available to everyone's agent.
• Team Gateway. One gateway for the team's Discord, Telegram, Slack and WhatsApp, plus the terminal, desktop apps and the cloud.
• Roles. Invite members by email. Owners and admins manage roles, spend caps and API keys; members just sign in and use their agents.
• A separate Enterprise tier. Business runs on Nous infrastructure with self-serve setup; Enterprise runs on infrastructure you control, with SSO, SLAs and white-glove onboarding.

Setup: there's no CLI command for teams. You set it up in the Portal: create the team, set a cap per member, invite people by email.

The obvious fits are the shared use cases already on this list: a team version of the competitor report (use case 15), the lead generation job (use case 5), Notion and Linear work (use case 22), or a shared assistant in your team's Slack or Discord. Until Nous publishes pricing, budget a pilot with a small balance and tight per-member caps, or keep running the open-source gateway.

Which use case should you start with?

If you're new to Hermes, start with one that's low effort and shows value in a day:

1. Daily inbox digest (10) if email runs your day.
2. Family WhatsApp assistant (11) if you want something the whole household uses.
3. Monitors that remember (17) for any price, news or competitor watch.
4. Notion and Linear connectors (22) if your work lives in those apps.

Then add one scheduled job a week. The agent gets more useful as its memory and skills build up.

More Hermes Agent ideas from the community

These are setups people have shared publicly in community roundups. We haven't verified them ourselves, so treat them as ideas rather than recipes:

• An autonomous sales rep that finds leads, qualifies buyers, writes outreach and keeps the pipeline updated.
• A content pipeline from trend discovery through drafting to publishing.
• Overnight coding "swarms" where several agents work a backlog with little supervision.
• Bedtime stories for kids, generated fresh each night.
• A nutrition coach that remembers what you ate and plans the week.
• Prediction-market and trading research bots.
• Multi-platform social media research that sums up what people say about a topic.
• Companies run almost entirely by agents, as an experiment in how far the setup can go.

If you build one of these, the use cases above usually have the building blocks: cron jobs (4, 9, 15, 17), parallel research (18), connectors (22) and memory (2).

What all of these have in common

Here's what no one tells you about these use cases.

The common thread isn't AI capability. It's persistence. Every use case above works because Hermes runs continuously, remembers across sessions, and works through messaging channels people already use. The model does the thinking. The infrastructure does the living. If you'd rather not own that infrastructure, a hosted AI agent builder supplies the always-on layer for you.

Three things repeat across all 25:

1. It lives in messaging. WhatsApp, Telegram, Discord, Slack, Feishu. The agent is where you already are. Not a separate app. Not a browser tab. A chat thread.

2. It runs on a schedule. Cron jobs for daily digests, weekly reports, price monitoring and content analysis. The agent works while you sleep, and since v0.21.0 those jobs remember their previous runs.

3. It gets smarter over time. Persistent memory (MEMORY.md, USER.md), a personality file (see our SOUL.md guide) and self-created skills. The agent learns your preferences and builds reusable playbooks from experience.

These three are exactly what BetterClaw provides as a managed platform. If you want messaging integration, scheduled automation and persistent memory without managing your own Hermes or OpenClaw infrastructure:

• Telegram, Slack, Discord and Gmail, plus webhooks and 500+ connectors, and any MCP server.
• Scheduled tasks and persistent memory.
• Several agents working together in one Project, the managed version of use cases 6 and 16.
• Bring your own key from 28+ providers with zero markup, or run local models through the BetterClaw desktop app.
• About 60 seconds to deploy.

Starter is $19 a month, Pro is $49 for 5 agents, and every plan starts with a 7-day trial. The use cases are the same. The infrastructure management is ours. Start here →

Frequently Asked Questions

What is Hermes Agent used for? Hermes Agent is used for always-on AI automation through the chat apps people already use. The most common use cases are daily inbox digests, family and team assistants on WhatsApp or Slack, competitor and price monitoring, lead generation, code review with Claude Code, and multi-agent teams. Recent releases added app connectors for Notion and Linear, one-click local models, voice with wake words, a password-blind credential vault, and a live Bot Screen you can take over.

What can Hermes Agent do? It can orchestrate Claude Code, share memory with other coding agents, tune and run local models, write weekly content gap reports, find sales leads, run a multi-agent fleet on one laptop, control a car or smart home, process health data locally, watch prices, send a morning inbox digest, run a family WhatsApp assistant, build a visual novel, hand off video production, power a translation extension, deliver competitor reports, host named bots in one group chat, steer parallel research, answer by voice, run logged-in errands without seeing passwords, summarize Teams meetings, and work inside Notion and Linear.

What's the best first use case for Hermes Agent? A daily inbox digest or a monitor that remembers past alerts. Both take minutes to set up with one hermes cron create command, show value the next morning, and teach you how scheduling, skills and delivery channels work before you try anything bigger.

Where can I find Hermes Agent user stories? Nous Research keeps a user stories page, and users post setups on X, GitHub and community forums. Use cases 1 to 15 on this page are drawn from those stories; 16 to 25 come from Hermes's release notes.

How does Hermes Agent compare to OpenClaw for these use cases? Both handle similar automation. Hermes has stronger goal persistence (/goal, Kanban), self-maintaining skills (Curator), and tighter security defaults (redaction on by default). OpenClaw has the larger ecosystem: about 394,000 GitHub stars to Hermes's about 260,000 as of November 2026. BetterClaw provides the same automations as a managed platform without self-hosting either; see how Hermes Agent compares with BetterClaw.

Can non-technical users set up Hermes Agent? More easily than before. Since v0.22.0, a fresh desktop install opens on a guided setup chat that runs on a free trial model, so you can start before you have an API key, and Hermes speaks 16 languages. Basic use cases (WhatsApp assistant, daily digest) are within reach for most people. Multi-agent fleets, custom skills and MCP still need technical comfort. BetterClaw is a no-code alternative with similar always-on messaging.

Can Hermes Agent run fully offline? Yes, for the model. Since v0.22.0 Hermes can download and run open models on your own machine with no account or API key, picking a build that fits your hardware. Use cases that reach the web, email or other apps still need those services online.

How much does it cost to run Hermes Agent? Hermes itself is free and open source. Self-hosted, you pay for model usage and a computer or small VPS (about $5 to $10 a month), or nothing for the model if you run it locally. Nous changed its paid plans on October 27, 2026: new Plus ($20), Super ($100) and Ultra ($200) plans each include a cloud agent (4 GB RAM and 25 GB disk on Plus, up to 8 GB RAM and 100 GB disk on Ultra), with usage limits that reset daily, weekly and monthly instead of monthly credits. Extra credits pay for API key usage, bigger agents and extra agents. Our Is Hermes Agent free? guide breaks it down. BetterClaw's managed plans start at $19 a month (Starter, 1 agent) or $49 (Pro, 5 agents), with your own model key.

Is Hermes Agent reliable enough for production use cases? For the use cases documented here, yes. Multiple users report weeks of continuous uptime with systemd. Releases still move fast, but v0.22.0 added tested SemVer stable releases that installs follow by default, plus signed desktop packages and a Microsoft Store build. Stay on the stable channel for anything you depend on, run hermes backup before upgrading, and note two v0.22.0 behaviour changes: chats no longer reset on an idle or daily timer, and one gateway now serves every profile on a machine. When something breaks, our Hermes Agent not working guide covers the most reported failures on the current release. For reliability without managing infrastructure, BetterClaw runs the agent for you.

Related Reading

• Hermes Agent alternatives: six options ranked by time to a working agent → /blog/hermes-agent-alternative
• Is Hermes Agent free? What costs nothing and what doesn't → /blog/is-hermes-agent-free
• Hermes Cloud vs BetterClaw: pricing and what you still manage → /blog/hermes-cloud-vs-betterclaw
• Hermes Agent not working: the most reported fixes → /blog/hermes-agent-not-working
• OpenClaw vs Hermes: capability against comprehensibility → /blog/openclaw-vs-hermes