372 results for “skills”
- What can Hermes do that Claude Code, ChatGPT or other assistants can't?FAQ · ComparisonsThe differences are mostly about where it runs and who controls it. Hermes is open source (MIT) and runs on your own machine, a server or a hosted instance, so it can stay on…
- What is Hermes Agent?FAQ · Getting startedHermes Agent is an open-source AI agent built by Nous Research. You can chat with it in a terminal, a desktop app, or through messaging apps like Telegram and Discord, and it…
- What's the best way to start learning Hermes?FAQ · Getting startedIf you don't want a terminal, install Hermes Desktop: first-run onboarding gets you to a first message quickly, and you can connect Nous Portal (one sign-in for models plus web…
- What's the difference between plugins and MCP servers?FAQ · Skills, plugins & MCPPlugins are Python packages in ~/.hermes/plugins/ (a plugin.yaml manifest plus code) that add tools, hooks and integrations directly inside Hermes. Install them with hermes…
- Which memory setup should I use: built-in, Honcho, Hindsight, Mem0, Obsidian or something else?FAQ · Memory & contextStart with built-in memory. It's always on, costs nothing extra, and together with session search covers most personal use. An external provider is additive: it runs alongside…
- Why aren't my scheduled jobs running?FAQ · Automation & schedulingAgent-backed cron jobs run inside the gateway, which checks for due jobs every 60 seconds. If the gateway isn't running, those jobs are skipped with a logged reason and fire on…
- Why does Hermes lose track in long sessions, and what does “context is over the compression threshold” mean?FAQ · Memory & contextLong conversations fill the model's context window, so Hermes compresses older history automatically, by default at 50% of the context limit (`compression.threshold`). Run…
- An e-commerce SEO agency gives Hermes separate Shopify, search and meeting-prep rolesCase study · Business operationsJim Stewart of StewArt Media describes using Hermes as an internal agent system for his agency, with separate sub-agents for Shopify engineering, search engineering and client meeting preparation. The interesting part is the order it follows on client sites: diagnose, propose, back up, then fix.
- How Razorpay runs one isolated, always-on Hermes agent per employee on KubernetesCase study · Business operationsRazorpay's engineering team describes a platform that gives each of 220+ employees their own Hermes agent, running in a separate Kubernetes namespace with locked-down network egress, audited outbound calls and hourly ingestion of the person's work data. It is a detailed public example of running Hermes as a multi-tenant internal service rather than a personal laptop tool.
- Running a Karpathy-style LLM wiki through a Telegram bot on a small VPSCase study · Research & knowledge workThe author replaced a hand-maintained Obsidian vault with a markdown wiki that Hermes Agent keeps up to date: sources get sent to a Telegram bot, and the agent files, cross-links, logs and lints them. What makes it interesting is that the agent does the bookkeeping. The author still picks what goes in.
- Ten fixes for running Hermes as an always-on Railway service with a Telegram botCase study · Skills, plugins & MCPThe author packaged Hermes in her own Docker image, deployed it to Railway as a persistent gateway, and connected Telegram, Notion MCP and fallback models. She wrote up the ten problems that cost her time. Most are general container lessons that apply to any Docker-based Hermes host.
- Hermes Agent MCP tool missing or failingTroubleshooting · Skills, plugins & MCPSeparate discovery, connection, authentication and operation failures using one known read-only request.
- Hermes Agent on Windows: command not found and other fixesTroubleshooting · Running & deployingWork through the documented Windows pitfalls for native installs and WSL2, from PATH and encoding to editors, shell scripts and the login-time gateway task.
- Hermes Agent profiles: separate agents for separate jobsGuide · Running & deployingHow Hermes profiles give you independent agents on one machine, what they isolate (and what they don't), and the commands for creating, switching, sharing and running them.
- Hermes Agent SOUL.md and personalities explainedGuide · Models, providers & costUse SOUL.md for the durable identity and tone of your agent, /personality for temporary modes, and AGENTS.md for project rules, so each layer does one job.
- Hermes Agent vision: send it screenshots and imagesGuide · Skills, plugins & MCPHow to attach images in the terminal or from chat apps, how Hermes routes them for vision and text-only models, and the settings that keep image-heavy sessions affordable.
- Hermes Agent web dashboard: a quick tourGuide · Running & deployingWhat the local dashboard can do, which pages save you the most time, and how to reach it from another machine without exposing your API keys.
- How Hermes Agent memory works (and where it stops)Guide · Memory & contextA plain-English tour of Hermes's two built-in memory files, the frozen snapshot they load into, their hard size limits, and when an external memory provider or session search is the better tool.
- How to keep Hermes Agent costs downGuide · Models, providers & costWhere Hermes spends tokens, how to measure it, and the documented settings and habits that keep your provider bill predictable.
- How to run Hermes Agent in DockerGuide · Getting startedHermes Agent has an official Docker image for amd64 and arm64. Run the setup wizard, then start the gateway with your data on a mounted volume.