Hermes Agent · for small & mid-size business

Meet your new hire:
an agent that never clocks out.

Hermes Agent is the open-source, self-improving AI agent built by Nous Research. Bit-Sulting deploys it locally for your business — installed, integrated, hardened, and taught to do real work.

What Hermes actually is

Not a coding copilot tethered to an IDE, and not a chatbot wrapper around a single API. Hermes is an autonomous agent that gets more capable the longer it runs. It lives wherever you put it — a spare mini PC, a $5 VPS, or a GPU box — and you talk to it from the apps you already use: Telegram, WhatsApp, Discord, Slack, or Teams, while it works on hardware you control.

Its defining feature is the built-in learning loop: Hermes creates skills from experience, improves them during use, nudges itself to persist what it learns, and builds a deepening model of who you are and how your business works — across sessions, across months.

Hermes Agent is MIT-licensed open source (github.com/NousResearch/hermes-agent), actively developed by Nous Research — the lab behind the Hermes family of models. Bit-Sulting is an independent deployment and support practice built on it.

What's in the box

🧠

Persistent memory

Remembers your preferences, your customers, your conventions — injected into every session.

📚

Self-written skills

After a hard task it saves the procedure as a reusable skill — compatible with the open agentskills.io standard.

💬

Messaging gateway

Telegram, WhatsApp, Discord, Slack, Teams and more. Your team messages the agent like a coworker.

Scheduled automations

Built-in cron: morning briefings, invoice chases, price watches, watchdog alerts — delivered anywhere.

🌐

Web & browser tools

Search, extract, drive a real browser, generate images, read documents — 60+ built-in tools.

🎙️

Voice mode

Real-time voice interaction in the CLI and on Telegram/Discord. Hands-free ops.

🤝

Bot teams

Bot Mode: named specialist bots, each with its own model, memory and skills, coordinating in group chats.

🛡️

Built-in guardrails

Command approval, authorization policies, container isolation. You decide what it may touch.


What SMB agents actually do all day

Real workflows we deploy. Each one starts as a conversation and ends as a scheduled skill.

Inbox triage & draftingSorts incoming mail, flags urgent, drafts replies in your voice for one-tap approval.
Invoice chasingWatches outstanding invoices, sends polite escalating reminders, reports what's still open.
Quote from emailReads a customer request, pulls your price list, drafts a formatted quote with your margin rules.
Morning briefingDaily digest at 8:00 — sales, calendar, open tickets, anything you track. Any channel.
Price & stock watchMonitors suppliers or competitors on a schedule and alerts only when something actually changes.
Report generationTurns CSVs and databases into weekly PDF/Excel reports without anyone copy-pasting.
Social & content draftsDrafts posts and updates from your notes; you approve before anything publishes.
On-call watchdogWatches your servers, services or backups and pings you the moment something breaks.
Micropayments on LightningAgent pays per-use APIs, data feeds and compute in sats — inside a budget you set, reconciled automatically.
Stablecoin invoicingIssues, chases and reconciles USDT/USDC invoices through the payment systems you already run.

Your agent, with a wallet, open for business

AI agents are becoming economic actors — paying for what they consume, collecting what they're owed, settling with each other. Bit-Sulting wires those rails into your deployment, from sats to stablecoins.

Lightning wallet per agent

Each agent can carry its own Lightning wallet: receive payments, pay per-use APIs, data feeds and compute in sats, and settle with other agents — instantly, at near-zero cost. Micropayments finally make business sense.

💵

USDT & USDC via systems already in use

Stablecoin flows through the processors, exchanges and on/off-ramp systems your business already trusts — fiat-stable value, programmable settlement, no new infrastructure to learn.

🛡️

Spend rules you own

Per-transaction caps, daily budgets, human approval above thresholds, and an audit trail you can actually read. The agent spends, the math verifies, you set the limits — #BetOnMath applied to money.

RailBest forHow it settles
Bitcoin / LightningMicropayments, pay-per-use APIs & data, agent-to-agent commerceSats — instant, near-zero fees
USDT / USDCInvoicing, supplier payouts, international settlementStablecoins via your existing processors & on/off-ramps
Your fiat railsEverything the business already does todayYour bank & processor, unchanged — the agent just does the work around them
Honest scoping: payment rails are integrations we build and harden on top of Hermes — open protocols plus the payment systems you already run. Every deployment starts read-only: the agent drafts, you approve. Actual payments unlock only once your guardrails are proven.
"It's not tied to your laptop. It lives where you put it — and it gets better at your business every week."
— why we chose Hermes

Where does it run?

OptionWhat it isGood for
Spare desktop / mini PCAny x86 box in your office, repurposed as the agent host.Zero new hardware cost. Our default recommendation.
NAS / home serverDocker deployment alongside your existing services.Businesses that already run a NAS.
$5 VPSSmall cloud instance; agent reachable 24/7.Always-on messaging automations, remote teams.
GPU box + local modelsLocal LLMs via Ollama/llama.cpp — zero API calls, fully private.Strict data privacy needs; maximum sovereignty.
Cloud model APIsPoint the agent at frontier models when you want top-end reasoning.Hard reasoning tasks; mix-and-match per bot.

Most SMB deployments start on a repurposed box with a cloud model for reasoning and local guardrails — then migrate workloads local as needs grow. We design that path with you.

Three ways to bring an agent on board

Every engagement starts with a free discovery call. Pricing is quoted per deployment — no mystery retainers, no per-seat fees to the software itself.

Kickstart

One agent, one workflow, live in days

Hermes installed on your hardware or VPS, security hardening, one channel wired up (e.g. Telegram), and one real workflow automated end-to-end. Your team gets a hands-on walkthrough.

Deploy · most popular

Full integration across your business

Multiple channels, scheduled automations, custom skills built from your actual processes, backups, monitoring, and training for everyone who'll talk to the agent. Payment rails — an agent Lightning wallet and stablecoin flows — included where they make sense.

Care

Agent ops on retainer

Updates, health monitoring, new skills as your needs grow, priority troubleshooting. Your agent keeps compounding while we keep it healthy.

$curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

Prefer to try it yourself first? That's the spirit. Install it, or let us do it right the first time.

Honest answers

Is my business data sent to the cloud?

Your choice. With cloud model APIs, prompts go to the model provider — just like any AI assistant. With local models (Ollama/llama.cpp on your own GPU or CPU), everything stays on your hardware. We help you pick the right mix and label exactly what goes where.

What does it cost?

The software is free — MIT licensed, no per-seat fees. Your costs are hardware you likely already own, any model API usage you choose, and Bit-Sulting's deployment/support fees, quoted up front after a discovery call.

Can it break things on my network?

Only what you allow. Hermes ships with command approval, authorization policies and container isolation, and we add firewall rules and least-privilege configuration as standard. Dangerous actions require your explicit sign-off.

Can the agent actually move money?

Yes — and only as much as you allow. Payment rails go in as integrations: a Lightning wallet for sats and micropayments, USDT/USDC through payment systems you already use. Everything starts read-only (the agent drafts, you approve), and spend caps, approval thresholds and a full audit trail are in place before your agent pays anything on its own.

Which messaging platforms work?

Telegram, Discord, Slack, WhatsApp, Microsoft Teams and more through the built-in messaging gateway. Your team messages the agent exactly like they message each other.

Do you lock us in?

No. Hermes is open source, its skills are portable markdown (agentskills.io compatible), and your config and memory live on your machine. If you ever want to run it without us, everything is yours — we'll even document how.

What can't it do?

We'll tell you on the discovery call. Agents are powerful but not magic — judgment-heavy decisions, legal commitments, and anything safety-critical stay with humans. The agent handles the grind; your people handle the calls.

See it running on your workflows

Book a free discovery call — bring one repetitive task you hate, and we'll show you how the agent would take it.