# DeployHermes

> DeployHermes is managed hosting for persistent Hermes bots: AI agents that each have a name, a role, a model, their own memory, and their own skills. Hermes Agent is the agent runtime, not a model provider — you connect your own supported provider credentials (Anthropic, OpenAI, Google Gemini, xAI Grok, or OpenRouter), and every workspace gets an isolated private runtime for an early-bird $99/month platform fee versus a $249/month list price until 2026-09-10 UTC, with model usage billed by your provider at their own rate.

You give a bot a mission and it reports back. Work lands on a shared board, anything needing judgement stops as a decision ticket until a human answers, and every execution leaves a receipt with its model, tokens, tools, duration, and result. Bots are steered from the web application or from Telegram.

The public library below is the product documentation: setup guides per channel and per provider, honest comparisons against self-hosting and against using a chat product directly, security and privacy guidance, self-hosting tutorials, technical explainers on cost and context, and troubleshooting pages written around a visible symptom.

## Product
- [DeployHermes — Managed Hermes Bot Hosting](https://deploy-hermes.com/): Hire a bot, not a server. What ships with each workspace, pricing, and the answers to the questions people ask before signing up.
- [Roadmap](https://deploy-hermes.com/roadmap): What has shipped, what is being built, and what is planned.

## When to use DeployHermes
- Use DeployHermes when the job is to operate a persistent AI-agent workspace, not to get a one-off chat completion.
- Reach for it to inspect bots, missions, tickets, runs, docs, memory, and integrations, or to create missions, answer approvals, write docs, and manage schedules over MCP.
- Start at the DeployHermes developer portal (/developers) or the public REST index (/api/v1), then read the OpenAPI contract, then call tools/list on the headless MCP endpoint with a workspace API key.

## Developer resources
- [DeployHermes Developer Portal](https://deploy-hermes.com/developers): API keys and scopes, the public REST endpoints, Markdown content negotiation, the headless MCP endpoint, the CLI, and the rate and credit limits.
- [Public REST API](https://deploy-hermes.com/api/v1): Unauthenticated discovery index. Also serves /api/v1/health, /api/v1/mcp, /api/v1/docs, and /api/v1/docs/{category}/{slug} as structured JSON.
- [OpenAPI](https://deploy-hermes.com/openapi.json): Machine-readable contract for the public discovery REST endpoints and the headless MCP JSON-RPC endpoint.
- [MCP server card](https://deploy-hermes.com/.well-known/mcp.json): Streamable HTTP endpoint, supported protocol versions, and the bearer header the workspace API key goes in.
- [MCP server card (server-card.json)](https://deploy-hermes.com/.well-known/mcp/server-card.json): The same server described at the second discovery path MCP clients probe, with every advertised tool named.
- [Authentication guide](https://deploy-hermes.com/auth.md): How an agent obtains a credential, the five scopes a key can carry including elevated manage_connections authority, the error shapes, and how a key is revoked.
- [Pricing](https://deploy-hermes.com/pricing.md): The current workspace fee, what usage credits pay for, and the per-key rate limits, in machine-readable markdown.
- [Natural-language query endpoint](https://deploy-hermes.com/ask): NLWeb-conformant. POST or GET a question and get ranked answers from this documentation as JSON, or as an SSE stream.
- [Markdown homepage](https://deploy-hermes.com/index.md): Every public page also answers to a .md suffix, and to Accept: text/markdown on its canonical URL.
- [API catalog](https://deploy-hermes.com/.well-known/api-catalog): RFC 9727 linkset pointing at the OpenAPI description, the developer portal, and the health endpoint.
- [A2A agent card](https://deploy-hermes.com/.well-known/agent-card.json): Agent-to-agent identity, capabilities and skills for this workspace surface.
- [Agentic Resource Discovery catalog](https://deploy-hermes.com/.well-known/ai-catalog.json): One document naming every agentic resource this site publishes.
- [Protected resource metadata](https://deploy-hermes.com/.well-known/oauth-protected-resource): RFC 9728: the resource identifier, the scopes a key can carry, and how the bearer token is presented.
- [Developer llms.txt](https://deploy-hermes.com/developers/llms.txt): Scoped context for the developer surface alone, instead of the whole manual.
- [API keys](https://deploy-hermes.com/settings/api-keys): Signed-in app path for creating a workspace API key; each reveal includes the exact mcpUrl to use.

## Getting Started
Beginner-friendly explainers for understanding Hermes Agent, hosted AI agents, and common first use cases.

- [Getting Started hub](https://deploy-hermes.com/getting-started): These pages answer the questions people ask before they are ready to deploy: what Hermes is, why an AI agent is different from a chatbot, and where it fits into day-to-day work.
- [What Is Hermes Agent?](https://deploy-hermes.com/getting-started/what-is-hermes-agent): A practical explanation of what Hermes Agent is, how it differs from a chatbot, and why people deploy it into real channels.
- [Why Use an AI Agent?](https://deploy-hermes.com/getting-started/why-use-an-ai-agent): Why teams move from one-off AI chats to persistent agents that can remember context, use tools, and act across time.
- [Daily Routines With AI Agents](https://deploy-hermes.com/getting-started/daily-routines-with-ai-agents): Examples of daily routines that persistent AI agents can own, from reminders and summaries to research and recurring check-ins.
- [AI for Founders](https://deploy-hermes.com/getting-started/ai-for-founders): How founders can use Hermes Agent for recurring operational work, research, channel triage, and lightweight execution.
- [AI for ADHD](https://deploy-hermes.com/getting-started/ai-for-adhd): How persistent AI agents can support ADHD-friendly routines, prompts, reminders, and low-friction task follow-through.
- [Sharing an AI Agent With Your Team](https://deploy-hermes.com/getting-started/sharing-an-ai-agent-with-your-team): What changes when an AI agent moves from personal assistant to shared team operator inside a supported channel or the web application.
- [What Is a Grok Bot? Models, Bots, and Agents Explained](https://deploy-hermes.com/getting-started/what-is-a-grok-bot): Learn what a Grok bot is, how xAI's Grok model family fits into an app, and where Hermes Agent fits when you need an agent runtime.
- [AI Bot vs AI Agent: What Is the Difference?](https://deploy-hermes.com/getting-started/ai-bot-vs-ai-agent): Compare an AI bot with an AI agent by looking at state, tools, goals, permissions, and the work each can reliably complete.
- [How to Choose an AI Model for Your Bot](https://deploy-hermes.com/getting-started/choosing-an-ai-model-for-your-bot): A practical framework for choosing an AI model for a bot based on task quality, latency, tool use, reliability, privacy, and cost controls.

## Setup Guides
Channel, provider, and deployment setup guides for launching Hermes Agent with less friction.

- [Setup Guides hub](https://deploy-hermes.com/setup-guides): These setup guides focus on the moving pieces that usually slow down first-time launches: channels, provider keys, and how to avoid dead-end configuration choices.
- [Telegram Setup](https://deploy-hermes.com/setup-guides/telegram-setup): How to set up Hermes Agent for Telegram with the right bot credentials, pairing flow, and first verification steps.
- [Discord Setup: DeployHermes Support Status](https://deploy-hermes.com/setup-guides/discord-setup): The current DeployHermes status for Discord chat deployment, retained at the original URL for accurate search guidance.
- [Slack Setup: DeployHermes Support Status](https://deploy-hermes.com/setup-guides/slack-setup): The current DeployHermes status for Slack chat deployment, retained at the original URL for accurate search guidance.
- [OpenAI Setup](https://deploy-hermes.com/setup-guides/openai-setup): How to connect Hermes Agent with the current Sign in with ChatGPT flow and verify the provider connection.
- [Anthropic Setup](https://deploy-hermes.com/setup-guides/anthropic-setup): How to configure Hermes Agent with Anthropic Claude credentials and avoid the most common validation mistakes.
- [Multi-Provider Setup](https://deploy-hermes.com/setup-guides/multi-provider-setup): How to think about multi-provider Hermes deployments using OpenAI, Anthropic, OpenRouter, and other LLM backends.
- [Grok and xAI Setup for Hermes Agent](https://deploy-hermes.com/setup-guides/grok-xai-setup): Connect an xAI API key to DeployHermes, understand validation, and confirm that the Grok provider is ready for an agent run.
- [How to Set Up a Grok Telegram Bot with Hermes Agent](https://deploy-hermes.com/setup-guides/grok-telegram-bot): Use Telegram as the supported bot channel and xAI as the model provider for a Hermes Agent workflow.
- [Google Gemini Setup for Hermes Agent](https://deploy-hermes.com/setup-guides/gemini-setup): Connect and validate a Google Gemini API key in DeployHermes, then test a provider-backed Hermes Agent run.
- [OpenRouter Setup for Hermes Agent](https://deploy-hermes.com/setup-guides/openrouter-setup): Connect an OpenRouter API key to Hermes Agent and understand authentication, model policy, and fallback tradeoffs.

## Comparisons
Side-by-side comparisons between DeployHermes, self-hosting, ChatGPT, custom GPTs, and other deployment approaches.

- [Comparisons hub](https://deploy-hermes.com/comparisons): Comparison content helps visitors decide whether they need a hosted agent, a hosted model, a self-managed runtime, or a simpler tool entirely.
- [Hermes Agent vs ChatGPT](https://deploy-hermes.com/comparisons/hermes-agent-vs-chatgpt): A practical comparison of Hermes Agent and ChatGPT, including persistence, tool use, channel integration, and operational tradeoffs.
- [DeployHermes vs Self-Hosting](https://deploy-hermes.com/comparisons/hermes-host-vs-self-hosting): What you gain and lose when choosing DeployHermes instead of running Hermes yourself on a VPS or local infrastructure.
- [Hermes vs Custom GPTs](https://deploy-hermes.com/comparisons/hermes-vs-custom-gpts): How Hermes compares with Custom GPTs for persistent workflows, channel integrations, and deployment ownership.
- [Managed vs Self-Hosted AI Agents](https://deploy-hermes.com/comparisons/managed-vs-self-hosted-ai-agents): A broader look at managed versus self-hosted AI agents, beyond Hermes alone, for teams choosing an operating model.
- [Local Models vs Hosted Models](https://deploy-hermes.com/comparisons/local-models-vs-hosted-models): How to compare local models and hosted models when deploying Hermes Agent for real workloads.
- [Hermes Agent hosting for persistent squads](https://deploy-hermes.com/hermes-agent-hosting): Host Hermes Agent without running your own VPS. DeployHermes gives each workspace an isolated runtime, a mission board, tickets, and receipts. Early-bird $99/mo vs $249 list until 2026-09-10 UTC; you bring your model provider.
- [Hermes Agent vs Grok: Runtime and Model Compared](https://deploy-hermes.com/comparisons/hermes-agent-vs-grok): Hermes Agent is an agent runtime and Grok is an xAI model family. Compare their roles so you can choose the right architecture.
- [Grok vs ChatGPT for AI Agents: Compare the Architecture](https://deploy-hermes.com/comparisons/grok-vs-chatgpt-for-ai-agents): Compare Grok and ChatGPT as provider choices for an AI agent without confusing a model service with the agent runtime around it.
- [Grok vs Claude for AI Agents: A Practical Comparison](https://deploy-hermes.com/comparisons/grok-vs-claude-for-ai-agents): Compare Grok and Claude as provider choices for an agent by testing quality, tools, authentication, privacy, and operational fit.

## Security & Privacy
Practical guidance on AI agent security, privacy, data handling, and deployment hardening.

- [Security & Privacy hub](https://deploy-hermes.com/security-privacy): AI agents touch tokens, prompts, channels, and memory. These pages clarify where the real security risks are and which controls actually reduce them.
- [AI Agent Security](https://deploy-hermes.com/security-privacy/ai-agent-security): A practical guide to AI agent security risks, controls, and deployment choices that actually reduce exposure.
- [Security Hardening Checklist](https://deploy-hermes.com/security-privacy/security-hardening-checklist): A security hardening checklist for AI agent deployments covering credentials, access, logging, channels, and recovery.
- [Privacy-First AI Agents](https://deploy-hermes.com/security-privacy/privacy-first-ai-agents): What privacy-first AI agents require in practice, from credential boundaries to retention choices and provider strategy.
- [AI Privacy Myths](https://deploy-hermes.com/security-privacy/ai-privacy-myths): Common myths about AI privacy, including assumptions about local models, hosted APIs, logs, and what 'private' really means.
- [Data Residency for AI Agents](https://deploy-hermes.com/security-privacy/data-residency-for-ai-agents): How to think about data residency for AI agents, including deployment regions, provider paths, and operational implications.
- [Grok Bot Security: Keys, Channels, and Agent Controls](https://deploy-hermes.com/security-privacy/grok-bot-security): Secure a Grok bot by protecting the xAI key, narrowing Telegram access, limiting tools, and verifying the complete agent boundary.

## Self-Hosting
Self-hosting tutorials, pitfalls, and managed-hosting comparisons for teams considering running Hermes themselves.

- [Self-Hosting hub](https://deploy-hermes.com/self-hosting): Self-hosting can be the right move, but most teams underestimate the time cost of Docker, bot credentials, volumes, uptime, and operational recovery.
- [Hermes Agent on Hetzner](https://deploy-hermes.com/self-hosting/hermes-agent-on-hetzner): What to expect when running Hermes Agent on Hetzner, including setup effort, tradeoffs, and when it may still be worth it.
- [Raspberry Pi Setup](https://deploy-hermes.com/self-hosting/raspberry-pi-setup): The reality of running Hermes Agent on a Raspberry Pi, including where it works, where it struggles, and what to watch.
- [Docker Setup](https://deploy-hermes.com/self-hosting/docker-setup): What Docker-based Hermes Agent setup looks like, including the convenience it provides and the complexity it does not remove.
- [5 Self-Hosting Mistakes](https://deploy-hermes.com/self-hosting/self-hosting-mistakes): Five common self-hosting mistakes people make when running Hermes or other AI agents, and how to avoid them.
- [VPS vs Managed Hosting](https://deploy-hermes.com/self-hosting/vps-vs-managed-hosting): A practical comparison of VPS hosting versus managed hosting for running Hermes Agent and similar AI workloads.

## Technical
Technical explainers for API pricing, context windows, memory systems, and cost control in AI agent deployments.

- [Technical hub](https://deploy-hermes.com/technical): These are the pages technical buyers and builders look for when they want to understand how agents behave under the hood and how costs actually accumulate.
- [AI Agent API Costs Explained](https://deploy-hermes.com/technical/ai-agent-api-costs-explained): How AI agent API costs accumulate across prompts, context, retries, tools, and recurring workflows.
- [API Pricing Guide](https://deploy-hermes.com/technical/api-pricing-guide): A practical API pricing guide for AI builders choosing providers and planning Hermes Agent workloads.
- [Reduce AI API Costs](https://deploy-hermes.com/technical/reduce-ai-api-costs): Practical ways to reduce AI API costs for Hermes Agent and similar LLM-powered workflows.
- [How AI Agent Memory Works](https://deploy-hermes.com/technical/how-ai-agent-memory-works): How AI agent memory works in practice, including what gets stored, what should not, and why memory design changes behavior.
- [Context Windows Explained](https://deploy-hermes.com/technical/context-windows-explained): A clear explanation of context windows, what they limit, and why they matter for Hermes Agent performance and cost.
- [How Hermes Agent Uses Grok Through xAI](https://deploy-hermes.com/technical/how-hermes-agent-uses-grok): Trace the path from an xAI API key to a Hermes Agent run and learn which layer owns authentication, execution, and Telegram delivery.
- [Choosing Models for Hermes Agent](https://deploy-hermes.com/technical/choosing-models-for-hermes-agent): Choose a model policy for Hermes Agent by separating task requirements, provider credentials, tools, fallbacks, and operational evidence.

## Troubleshooting
Troubleshooting guides for common Hermes Agent, provider, auth, and channel integration errors.

- [Troubleshooting hub](https://deploy-hermes.com/troubleshooting): These pages are written for real debugging sessions: a visible symptom, the likely causes, and a recovery order that gets you unblocked quickly.
- [Telegram Pairing Issues](https://deploy-hermes.com/troubleshooting/telegram-pairing-issues): How to troubleshoot Telegram pairing issues with Hermes Agent, from bot tokens to chat targeting and provider validation.
- [Discord Bot Permission Issues: DeployHermes Support Status](https://deploy-hermes.com/troubleshooting/discord-bot-permission-issues): The current DeployHermes status for Discord chat deployment, retained at the original URL for accurate search guidance.
- [Slack Auth Mismatch: DeployHermes Support Status](https://deploy-hermes.com/troubleshooting/slack-auth-mismatch): The current DeployHermes status for Slack chat deployment, retained at the original URL for accurate search guidance.
- [OAuth Expiry](https://deploy-hermes.com/troubleshooting/oauth-expiry): What OAuth expiry symptoms look like in Hermes deployments and how to refresh tokens without chasing the wrong cause.
- [No Output](https://deploy-hermes.com/troubleshooting/no-output): How to debug a Hermes Agent that appears online but produces no output in response to user prompts.
- [OpenAI 400 Error](https://deploy-hermes.com/troubleshooting/openai-400-error): How to debug OpenAI 400 errors in Hermes Agent, including malformed requests, model assumptions, and payload issues.
- [Context Overflow](https://deploy-hermes.com/troubleshooting/context-overflow): How to identify and fix context overflow problems in Hermes Agent workflows before they become cost and reliability issues.
- [WebSocket Payload Too Large](https://deploy-hermes.com/troubleshooting/websocket-payload-too-large): How to debug WebSocket payload too large errors in Hermes runtimes, terminals, or live-streamed agent features.
- [Fix Grok API Authentication Errors in Hermes Agent](https://deploy-hermes.com/troubleshooting/grok-api-authentication-errors): Diagnose xAI key rejection, missing provider credentials, and runtime authentication errors in a Grok-backed Hermes Agent.
- [Grok Telegram Bot Not Responding: A Recovery Checklist](https://deploy-hermes.com/troubleshooting/grok-bot-not-responding): Troubleshoot a Grok-backed Telegram bot that does not reply by checking pairing, runtime state, xAI authentication, and delivery in order.

## Company
- [About DeployHermes](https://deploy-hermes.com/about): How DeployHermes operates managed Hermes bot workspaces for teams that need durable AI-agent work.
- [Privacy Policy](https://deploy-hermes.com/privacy): How DeployHermes handles deployment credentials, user data, and runtime access.
- [Terms of Service](https://deploy-hermes.com/terms): Terms governing access to DeployHermes and managed Hermes deployments.
- [Talk to DeployHermes](https://deploy-hermes.com/contact): Contact DeployHermes for support, security questions, or deployment planning.

## Related searches this site answers
These are the phrasings people use for this product and this product category. They are listed so a retrieval system can match a question to the right page, and every one of them is true of what DeployHermes does.

### Product and hosting
- Hermes bot
- Hermes bot hosting
- managed Hermes bot
- how to deploy a Hermes bot
- Hermes AI bot
- Hermes Agent hosting
- hosted Hermes agent
- Hermes Telegram bot
- Hermes bot without a VPS
- run a Hermes bot for my business
- hire an AI bot
- persistent AI agent hosting
- AI agent as a service
- managed AI agent hosting
- always-on AI agent
- bring your own API key AI agent

### Category and job to be done
DeployHermes is a mission control for AI agents: a durable mission board, a named squad of bots, a human decision queue for anything needing judgement, and a run receipt for every execution.
- mission control for AI agents
- AI agent mission control
- mission control HQ for AI agents
- AI agent HQ
- AI workforce control plane
- AI agent operations dashboard
- AI agent mission board
- AI agent approval queue
- supervised AI agent team
- AI agent squad management

### Alternatives people compare
Listed comparatively. DeployHermes is not affiliated with, endorsed by, or equivalent to any product named here.
- MissionControlHQ alternative
- Mission Control HQ alternative
- alternative to a self-hosted agent runtime
- ChatGPT alternative for recurring business work
- custom GPT alternative
- alternative to running Hermes on your own VPS

## Optional
- [Full content catalogue](https://deploy-hermes.com/llms-full.txt): The complete text of every page above, in one file.
- [Sitemap](https://deploy-hermes.com/sitemap.xml): Every public URL with its last-modified date.
- [OpenAPI](https://deploy-hermes.com/openapi.json): Public discovery REST and headless MCP endpoint schema, with auth and JSON-RPC request shapes.

Sitemap: https://deploy-hermes.com/sitemap.xml