Learning Hub
Read by topic and stage
4Start guides
8Topics
12X examples
Hermes Agent Field Notes
Guides, technical notes, and community references for installing, configuring, and running Hermes Agent across models, gateways, memory, skills, browser control, and sandboxes.
Start here
A recommended reading path from first installation to a stable, long-running Hermes setup.
01020304
Install Hermes Agent
Start with platform support, the official install command, shell reload, and first-run setup.
Map Integrations
Understand messaging platforms, model providers, execution backends, MCP, browser, and voice surfaces.
Study Real Workflows
Read the X-sourced showcase for how early users are testing Hermes in creative, local-model, and operator workflows.
Answer Setup Questions
Use the FAQ for answers on official sources, supported platforms, models, cost, privacy, and migration.
Field notes
Topic tracks for practical guides, comparisons, and implementation notes.
01Install02Models03Gateways04Memory05Expansion06Runtime07Compare08Showcase
Installation and host setup
Platform notes for Linux, macOS, WSL2, Termux, shell reloads, first command checks, and doctor-style troubleshooting.
Model providers and routing
How to think about Nous Portal, OpenRouter, OpenAI-compatible endpoints, local models, auxiliary models, and switching costs.
Telegram, Discord, Slack, and mobile messaging usage
Patterns for running Hermes from messaging surfaces while the agent lives on a server, VPS, workstation, or sandbox.
Memory, session search, and procedural skills
Notes on persistent memory, USER.md, MEMORY.md, session recall, skill creation, and when to move knowledge into repeatable procedures.
MCP, browser, terminal, and tool expansion
How Hermes becomes a domain operator through MCP servers, browser automation, terminal tools, vision, voice, and custom skills.
Docker, SSH, Modal, and sandbox decisions
Tradeoffs for local execution, Docker isolation, remote SSH, serverless runtime choices, approval boundaries, and long-running machines.
Hermes vs OpenClaw and other agent stacks
Positioning notes for people comparing long-lived assistants, coding agents, hosted chat tools, and self-hosted operator frameworks.
Real user workflows and community research
Follow public X posts where Hermes users test video generation, local inference, memory design, setup guides, and gateway patterns.
Community examples
Recent public X posts that show how early Hermes users are testing creative, local-model, setup, and memory workflows.
Turn a screen recording into a tutorial video
Vicky gave Hermes Agent a screen recording and asked for a setup tutorial. The workflow produced a HeyGen video with her avatar and kept the user's preferences in memory for follow-up work.
Give Hermes domain-specific optimization skills
Alex used Hermes-Agent TurboQuant skills to apply, test, document, and package an optimization path for Qwen3.5-9B-MLX on Apple Silicon.
Patch local-runner context detection
Sudo documented a local-model context mismatch, patched a Hermes setup manually, and outlined a PR path to detect model name and context length from local runners.
Compare memory speed on the same Mac mini
Witcheer ran OpenClaw and Hermes on the same Mac mini and focused on Hermes' small prompt footprint, FTS5 session search, procedural skills, and faster response loop.
Official sources
Use these official links for documentation, releases, repository activity, and community support.
01020304
Hermes Agent Docs
Official documentation for installation, configuration, features, security, and architecture.
GitHub Repository
Source code, releases, issues, discussions, and the canonical README for Hermes Agent.
Nous Research
The lab behind Hermes, Nomos, and Psyche. Useful if you want broader context for the project.
Discord Community
Community support, release chatter, setup troubleshooting, and ecosystem discovery.
Planned guides
Topics to expand next based on common installation, integration, and operations questions.
Hermes gateway cookbook
Practical recipes for setting up chat-first Hermes workflows across messaging platforms without turning the agent into a black box.
Memory tuning field guide
A focused guide on what belongs in memory, what should become a skill, and what should stay in project context.
Sandboxing decisions for personal agents
A decision tree for local, Docker, SSH, and serverless execution when the agent is allowed to touch real files and services.