Hermes Agent setup guides for self-hosting and operations
If your intent is practical — install, connect, deploy, schedule, or migrate — this is the section to use. Start with the fastest install path, then branch into the exact integration or infrastructure guide you need.
Best pages to start with
Install Hermes Agent with the official CLI: handle macOS quirks, set an API key, run hermes doctor, open the dashboard, or pick FlyHermes cloud.
Step-by-step Hermes Telegram setup: BotFather token, human user ID, pairing, gateway restart, DM proof, groups/topics, and FlyHermes hosted path.
Connect Hermes Agent to Discord with bot intents, fail-closed users/roles/channels, thread sessions, gateway setup, provider smoke tests, and one real reply.
Configure Hermes Agent built-in memory, review MEMORY.md and USER.md, choose an optional external memory provider, and separate durable facts from session history.
Create a focused Hermes Agent skill with valid SKILL.md frontmatter, narrow triggers, supporting references or scripts, safety boundaries, and a repeatable acceptance test.
Create and verify Hermes Agent cron jobs with fresh-session prompts, workdir, script-only mode, provider safeguards, exact delivery, and recovery commands.
Deploy Hermes Agent on a VPS, understand the hidden maintenance cost, and decide when FlyHermes is easier for gateways, memory, and agents.
Set up Hermes Agent on WhatsApp with the Baileys QR bridge or Meta's official Cloud API, including allowlists, sessions, webhooks, voice notes, cron limits, and troubleshooting.
Connect Hermes Agent to Slack with the generated app manifest, Socket Mode tokens, user and channel allowlists, thread commands, cron delivery, and exact troubleshooting checks.
Connect Hermes Agent to Ollama with the current quick launch or manual OpenAI-compatible endpoint, then verify context, tool calls, privacy, and fallbacks.
Set up Hermes Agent with OpenRouter, choose models, control credits and spend, configure fallbacks, and troubleshoot rate limits or model switching.
Master the Hermes CLI for managing your agent, skills, memory, and configuration from the terminal.
Update Hermes Agent safely with current backup, preview, dependency, Desktop, Docker, Windows, gateway, and post-update verification steps.
Back up and restore Hermes Agent memory, profiles, sessions, skills, cron jobs, config, and credentials with the current Hermes CLI.
Run multiple Hermes agents with different personalities, skills, and channels — each with isolated memory.
Harden your Hermes Agent deployment with firewall rules, SSH keys, approval workflows, and best practices.
Set up Tirith approval workflows so Hermes asks permission before running dangerous or sensitive commands.
Use hermes claw migrate to preview and import OpenClaw memory, skills, providers, MCP servers, channels, and settings, then verify archived items and secrets safely.
Run Hermes Agent with the official Docker image, persistent /opt/data storage, supervised gateways, private dashboard access, logs, and safe updates.
Install Hermes Agent in one click using Pinokio — no terminal, no config files, just click and go.
Extend Hermes Agent with custom tools — shell scripts, APIs, MCP servers, and external integrations.
Enable voice input and output for Hermes Agent — talk to your AI and hear responses spoken back.
Run Hermes Agent completely offline with local models, local STT, and zero internet dependency.
Fix Hermes Desktop installation on Windows: PATH, enterprise npm proxy, missing dependencies, endless loading, provider setup, native Windows limits, and WSL2 choices.
Open Hermes Web UI on port 9119, keep it running with systemd on Linux, secure remote access, use browser Chat, and verify channels and cron jobs end to end.
Connect Hermes Agent to GitHub repositories for issue triage, PR reviews, Actions troubleshooting, code search, and repo management.
Sync memory, skills, and config across multiple Hermes Agent installations using backup, import, and sync tools.
Troubleshoot when Hermes acts like a basic chatbot instead of an agent — not executing tools, commands, or actions.
Connect Hermes Agent to Google Gemini models using Code Assist API OAuth, including 1M token context and multi-tool support.
Connect Hermes Agent to your email for AI-powered inbox management, auto-replies, and smart filtering.
Resolve issues when Hermes running via Discord suddenly appears inside a Docker container, losing access to config files and volumes.
Resolve common Copilot-ACP authentication and model errors when using GitHub Copilot as a provider in Hermes Agent.
Resolve issues where API keys won't paste during Hermes setup on WSL, Termux, or non-standard terminals.
Resolve the white square emoji rendering issues that appear in Matrix/Element when using Hermes Agent.
Configure Hermes Agent to execute terminal commands inside isolated Docker containers for security and reproducibility.
Configure Hermes Agent to execute commands on a remote server while keeping the agent code local — perfect for sandboxing.
Configure Hermes Agent to execute commands on Modal's serverless cloud infrastructure — GPU access, auto-scaling, pay only when active.
Configure Hermes Agent to execute commands in Daytona's managed cloud development environments — persistent workspaces with team collaboration.
Configure Hermes Agent to execute commands in Singularity containers — ideal for HPC clusters and shared compute environments.
Inspect Hermes context with /context, configure in-place compression, and recover long conversations without confusing context pressure with memory loss.
Connect local, Docker, and OAuth MCP servers to Hermes Agent safely. Fix mcp_servers YAML, container paths, remote auth, stale tools, and gateway reloads.
Enable voice interaction with Hermes — speak your commands, hear the responses with text-to-speech.
Configure Browser Use mode, browser_exec sessions, Lightpanda, Browserbase, Firecrawl, Camofox, or local Chrome CDP, then verify screenshots and console evidence.
Set up subagent spawning so Hermes can delegate tasks to child agents for parallel workstreams and complex orchestration.
Register shell scripts as callbacks for Hermes events — block dangerous commands, auto-format files, inject context, and log activity.
Control when messaging sessions automatically reset — balance context length, API costs, and conversation continuity.
Change Hermes CLI colors, spinner animations, branding, and response styling with built-in or custom skins.
Control how much 'thinking' the model does before responding — balance speed, cost, and reasoning depth.
Configure Hermes Agent to use Google's Gemini models directly via Google AI Studio — fast, capable, and cost-effective.
Configure Hermes Agent with Ollama’s local OpenAI-compatible endpoint, exact model discovery, context checks, and tool-call troubleshooting.
Configure Hermes Agent to use MiniMax models — powerful Chinese AI models with excellent reasoning capabilities.
Configure Hermes Agent to use Kimi Code models from Moonshot AI — excellent for coding tasks.
Configure Hermes Agent to use ZhipuAI's GLM models via z.ai — powerful Chinese language models.
Configure Hermes Agent to use 20+ open models via Hugging Face's unified inference endpoint.
Configure Hermes Agent to use NVIDIA NIM for optimized inference on NVIDIA hardware.
Configure Hermes Agent to use GitHub Copilot models via your existing Copilot subscription.
Configure Hermes Agent to use Xiaomi's MiMo models — excellent for auxiliary tasks and reasoning.
Configure Hermes Agent to use Arcee AI's Trinity models — specialized models for enterprise tasks.
Recover Hermes Desktop when it will not launch after an update without deleting profiles, memory, sessions, skills, or credentials.