Why these use cases are possible at all
Hermes runs in the background continuously, can reach out to you rather than waiting to be asked, has memory of past conversations, and can execute code and interact with websites. Not just generate text.
Think of it as a capable colleague who's available at 3am, remembers what you worked on last month, and actually does tasks rather than describing how you could do them. The full comparison with standard chatbots is worth reading if you want the deeper breakdown.
Everything below works through whatever messaging app you connect it to. Telegram is the most popular. Discord, WhatsApp, Email, and 11 others also work. You text it. It does the thing. It replies when done.
Morning briefings
Hermes has a built-in scheduler. You set it up once and it runs without you asking.
People send themselves: a daily weather + calendar summary, a portfolio snapshot pulled from a finance API, GitHub issues opened overnight, or just headlines filtered to topics they care about. The agent fetches everything, writes a summary, and sends it to Telegram before you're out of bed.
Setup is a one-time thing. Tell the agent what you want in conversation and ask it to schedule itself — it writes the cron entry and handles the rest. Or use a skill file if you want something more structured.
Monitoring and alerts
Because it runs 24/7, it can watch things and only message you when something changes. Worth setting up:
- Server uptime — ping your services every 5 minutes, alert on Telegram if one goes down
- Price tracking — check a product page and alert when the price drops below your target
- GitHub activity — watch a repo and summarise new issues or PRs when they land
- Job postings — check a careers page daily, alert only when new relevant roles appear
This is where running on a server rather than your laptop actually matters. Laptops sleep. The agent doesn't.
Coding assistant that knows your codebase
Hermes can read files, write files, run commands, and execute code. Point it at a source directory and ask it to find all usages of a deprecated function, write tests for something you just described, explain what a complex file does in plain English, or run the test suite and summarise what failed.
The part that gets genuinely useful over time: it remembers your project context across sessions. After a few weeks, you don't re-explain your tech stack or code style every time. It already knows.
For developers who want to understand the security model — how shell access is sandboxed, why non-root matters — the self-hosting guide covers it.
Browser automation
Full browser, not just URL fetching. Hermes can log into dashboards, fill in forms, extract data from pages that need JavaScript to work, take screenshots, and interact with things that a basic HTTP request can't touch.
Real setups people run: pulling weekly reports from a SaaS dashboard, filling timesheet fields across multiple days, downloading invoices from vendor portals, checking competitor pricing pages on a schedule.
Browser automation needs RAM — budget at least 2GB headroom above the agent's baseline. The VPS comparison has the hardware breakdown. Hetzner CX33 (8GB) handles it without issues.
File management and document processing
Hermes has full access to the server's filesystem, and if you mount cloud storage it can reach that too. Rename and organise files based on their contents. Convert a folder of PDFs to text. Extract data from spreadsheets. Archive old project folders on a schedule.
It reads PDFs, images (with vision), CSVs, most text formats. Output goes to a new file or back to you as a message, depending on what you ask for.
Email drafts
Connect it to an email account via IMAP/SMTP and it can draft replies, flag urgent messages, or monitor for specific types of incoming mail. Most common workflow: forward a thread to the agent on Telegram, ask for a draft reply, review it, send.
Not a replacement for a proper email client. Good for specific recurring things — drafting responses to job applications, writing newsletter updates, processing customer support emails into a structured format.
Research
Ask Hermes to research something and it browses actual sources, extracts the key points, and returns a summary with citations. It visits real pages — it doesn't describe what might be there.
People use it for competitor research, digging into a technical topic before a meeting, summarising a long PDF, or generating a company briefing before a call. Output goes to a file you can keep and edit.
Personal finance tracking
With API access to a bank, portfolio tracker, or expense tool, Hermes pulls financial data and sends weekly summaries to Telegram. Friday afternoon spending breakdown. Monthly P&L for freelancers. Morning portfolio snapshot.
Skills are the standard way to package up an API integration here — write it once, the agent calls it on schedule without re-explanation.
Home automation
Hermes supports Home Assistant as a native gateway — the same way it connects to Telegram, it can connect to your smart home. Control lights, heating, security, any connected device from anywhere.
Beyond direct control: it responds to sensor events. Alert if the front door opens between 10pm and 7am. Turn on the bedroom light at sunset. Message me if the temperature drops below 18°C.
Self-improving workflows
When Hermes solves a problem it expects to face again, it can write a skill — a reusable procedure — and use that skill next time. First time you ask it to run your deployment flow might take 5 minutes. After it documents the process, same task is faster and more predictable.
After six months of use, a Hermes instance has a skill library specific to your workflows. It knows your deployment process, your document formats, your code style — not because you trained it, but because it documented what worked.
Daily Telegram commands
This is what most people describe as their actual daily experience. They have Hermes on Telegram and just text it during the day. 'Remind me at 3pm to follow up with Alex.' 'Is my staging server up?' 'What was I researching last Thursday?' 'Draft an invoice for 12 hours at £150/hr.'
The agent handles individual requests, uses tools as needed, remembers past sessions, and replies when done. For people in this pattern, it replaces a lot of small tasks that used to pile up in a to-do list.
API and business automation
Hermes makes HTTP requests, handles authentication, parses responses, and chains API calls. Webhook support means external services trigger the agent directly — Stripe, GitHub, JIRA, anything that can send a POST request.
Flows people actually run: new Stripe payment arrives → agent pulls customer info → sends a personalised welcome. GitHub PR opened → agent runs a code review and posts a comment. Support ticket created → agent categorises and drafts an initial response.
The gateway guide covers webhook setup.
How to get started
Two options: self-host it on a server (full guide here) or use Hermes OS which handles the server, setup, and maintenance and has you running in under 5 minutes.
Self-hosting costs around $10-25/month total. Hermes OS starts at $19/month with no server to manage. Full cost breakdown here.