Managed Hermes hosting
Nous Research's open-source autonomous agent — deployed, kept online, and updated by HostAgentes. Hermes lives in Telegram, Discord, Slack, WhatsApp, Signal, and Email at once, with persistent memory and subagent delegation, without you managing the gateway process or sandbox infrastructure.
Unlimited agents. Unlimited runs. Persistent memory included. From $9.99/mo.
What is managed Hermes hosting?
Hermes Agent is an open-source (MIT-licensed) autonomous AI agent built by Nous Research. It connects to Telegram, Discord, Slack, WhatsApp, Signal, Email, and CLI through a single messaging gateway, keeps persistent memory across sessions, delegates work to isolated subagents, and runs tool calls in a sandboxed backend (Docker, SSH, local, or a serverless option like Modal). Nous also ships a native desktop app for macOS, Windows, and Linux. Managed Hermes hosting means a third-party provider runs the gateway process and sandbox infrastructure for you, on always-on compute, instead of you self-hosting via Docker Compose.
HostAgentes offers managed Hermes hosting in three tiers: Basic at $9.99/mo (1 vCPU, 2 GB RAM, persistent memory included), Pro at $29.99/mo (2 vCPU, team management, production observability), and Scale at $79.99/mo (4 vCPU, multiple workspaces, target 99.9% uptime SLA). Unlike generic cloud platforms, HostAgentes charges for dedicated compute with no usage caps on agents or runs.
Every HostAgentes Hermes instance comes with the messaging gateway kept online 24/7, persistent memory storage, and a Docker sandbox backend pre-configured. SSL is provisioned automatically. Deployment takes under five minutes — you connect your channels and LLM keys, no Docker Compose or CLI setup required on your end.
Simple, transparent pricing
No run limits. No per-seat charges. Pay for compute, not usage.
Basic
For experimenting with Hermes and deploying your first autonomous agents.
- 1 vCPU, 2 GB RAM
- 20 GB storage
- Unlimited agents
- Unlimited runs
- Bring your own model keys (BYOK)
- Persistent memory (vector + KV)
- SSL and automatic backups
- Community support
Pro
For teams running production agents with team collaboration and advanced observability.
- Everything in Basic
- 2 vCPU, 4 GB RAM
- 50 GB storage
- Team management + roles
- Advanced agent orchestration
- Production observability dashboard
- Email support
- Automatic zero-downtime updates
Scale
For organizations with multiple high-traffic agent fleets and strict compliance needs.
- Everything in Pro
- 4 vCPU, 8 GB RAM
- 100 GB storage
- Multiple workspaces
- Enterprise SSO
- Priority support
- Target 99.9% uptime SLA
7-day money-back guarantee. Cancel at any time.
The price you see is the price you pay. No renewal surprises, no hidden fees.
The full Hermes stack, managed
Every feature Hermes ships — the messaging gateway, persistent memory, subagent delegation, sandboxed execution — live on your instance from day one.
Multi-channel connectivity
Hermes runs a single messaging gateway that connects your agent to Telegram, Discord, Slack, WhatsApp, Signal, Email, and CLI at once. HostAgentes keeps the gateway process online 24/7 so your agent stays reachable on every channel without you managing a persistent server.
Persistent memory
Hermes remembers context across sessions and projects. On HostAgentes, that memory store is provisioned, backed up, and scaled automatically alongside your instance — no separate database to configure.
Subagent delegation
Hermes can spin up isolated subagents to handle parallel or long-running pieces of a task, then fold the results back into the main conversation. This is native to Hermes' architecture, not a HostAgentes add-on.
Multi-model reasoning
Switch providers and models on the fly with Hermes' built-in /model command — OpenRouter, OpenAI, Anthropic, or any OpenAI-compatible endpoint. Your keys, your model costs; HostAgentes never proxies or marks up LLM calls.
Sandboxed execution
Hermes supports six terminal backends — local, Docker, SSH, Singularity, Modal, and Daytona — for running tool calls and code safely. HostAgentes runs your instance on the Docker backend by default, fully isolated per customer.
Natural-language scheduling
Ask Hermes to check something every morning or follow up next week and it schedules the task itself — no cron jobs or external schedulers to wire up.
Popular Hermes agents on HostAgentes
What teams actually build once they have a managed Hermes instance with persistent memory and no run caps.
Customer support agent
Index your help docs and past tickets into persistent memory. The agent answers tickets in real time, escalates to humans when confidence is low, and learns from resolved cases to improve future replies.
Sales automation pipeline
Connect Hermes to your CRM. The agent enriches leads, drafts personalized outreach, schedules meetings, and updates opportunity stages — all while retaining context about previous interactions.
Data processing worker
Ingest CSVs, PDFs, or API feeds on a schedule. The agent validates, transforms, and loads data into your warehouse, reporting errors and retries automatically without human intervention.
Research assistant
Give Hermes a topic and a set of sources. The agent searches the web, reads documents, synthesizes findings into structured summaries, and cites every source with direct links.
IT ops copilot
Monitor logs and alerts via webhook. The agent diagnoses common issues, runs predefined remediation playbooks, and opens tickets in your ITSM tool only when human approval is required.
Content moderation agent
Review user-generated content against your policy documents stored in memory. The agent flags violations, explains the rule triggered, and queues edge cases for human review with full context.
Configure Hermes in one file
Hermes is configured through its interactive hermes setup CLI wizard or a plain YAML config file — which channels to connect, which model to default to, and which sandbox backend to run tool calls in. HostAgentes provisions this on your instance and keeps it running.
# hermes setup — interactive CLI wizard, or edit cli-config.yaml directly
gateway:
platforms: [telegram, slack, whatsapp]
model:
provider: openrouter
default: anthropic/claude-sonnet-5
# Switch anytime from inside a chat with /model
sandbox:
backend: docker # local | docker | ssh | singularity | modal | daytona
memory:
persistent: true # retained across sessions automaticallyHostAgentes applies this config when your instance is provisioned. Add or remove channels anytime from your dashboard.
From zero to agent in 3 steps
Pick a plan and deploy
Choose Basic, Pro, or Scale. HostAgentes provisions the Hermes gateway process, persistent memory storage, and a Docker sandbox backend automatically. Your instance is live with a TLS endpoint in under 5 minutes.
Connect your channels and LLM keys
Link Telegram, Discord, Slack, WhatsApp, Signal, or Email to your gateway, and add your OpenRouter, OpenAI, or Anthropic API key. Switch models anytime from inside a chat with Hermes' /model command.
Talk to it, and let it run
Hermes picks up conversations and scheduled tasks across every connected channel, delegates work to subagents when needed, and retains context between sessions. Monitor uptime and usage from the HostAgentes dashboard.
Why HostAgentes for Hermes?
Hermes' gateway needs to stay online around the clock. HostAgentes runs that infrastructure so you don't have to keep a server up yourself.
The gateway stays online — no server to babysit
Self-hosting Hermes means keeping `hermes gateway` running 24/7 on your own machine or VPS. On HostAgentes, the gateway process, restarts, and updates are handled for you, so your agent stays reachable on every connected channel.
No per-run pricing trap
Generic agent platforms charge by execution volume: plans cap at a fixed run count and charge overages. HostAgentes charges for dedicated vCPU and RAM. Your agent can run and respond thousands of times a day — the bill stays the same.
Sandbox backend pre-configured
Hermes needs a sandbox backend (Docker, SSH, or a serverless option) for safe tool execution. HostAgentes provisions and isolates a Docker backend per customer by default — no manual container setup.
Pair it with Paperclip for orchestration
Hermes excels as a single autonomous agent with persistent memory living in your chat channels. For multi-agent orchestration with governance, budgets, and team collaboration, Paperclip is the right complement. Run both from the same HostAgentes account and let each tool do what it does best.
Frequently asked questions
What is Hermes Agent, and who makes it?
What does HostAgentes' managed Hermes hosting add?
Can I use my own LLM keys with Hermes?
Can I run Hermes and Paperclip on the same account?
Is agent memory encrypted at rest?
Deploy your Hermes instance
The messaging gateway, persistent memory, and sandboxed execution — live in under 5 minutes. Unlimited agents and runs from $9.99/mo.