HermesWatcher
Search⌘K For brandsSetup help
StartStart hereSetup plannerInstall Hermes AgentChat from your phoneYour first 24 hours
Use casesWorkflow blueprintsCase studiesUse-case collectionsCommunity libraryPrompt library
LearnWhat is Hermes Agent?GuidesTopicsFAQCommand cheat sheetGlossarySOUL.md gallery
ToolsTools & integrationsAll messaging platformsSkills directoryPlugins directorySkills, plugins & MCP
TroubleshootReleases
Work with usServicesNewsletterFor brands: partner with usFor AI agentsContactAboutFollow @HermesWatcher on X ↗ (opens in a new tab)

Search

All 139Guide 34Troubleshooting 8FAQ 36Tool & integration 14Workflow 3Glossary 7Community report 24

14 results for “cost”

  1. Models and providers: configure the actual inference routeTool & integration · Development & operationsUnderstand which model handles conversation and which auxiliary models handle supporting tasks before diagnosing quality or cost.
  2. API server: use Hermes from any OpenAI-compatible clientTool & integration · Running & deployingExpose Hermes as an OpenAI-compatible HTTP endpoint so chat frontends and scripts can talk to your agent.
  3. Browser tools: interact with pages when retrieval is insufficientTool & integration · Research & knowledge workUse a configured browser backend for navigation, visible page interaction, forms, and tasks requiring an authenticated session.
  4. Code execution: let the agent script multi-step tool workTool & integration · Skills, plugins & MCPThe execute_code tool lets Hermes write and run a Python script that calls its own tools, collapsing many steps into one.
  5. Discord: keep agent conversation scoped to the right peopleTool & integration · Everyday administrationConnect Hermes to direct messages or server channels with deliberate mention rules, authorization, and session boundaries.
  6. Fallback providers: keep working when your main model failsTool & integration · Models, providers & costDefine a chain of backup model providers that Hermes switches to on rate limits, outages or auth errors.
  7. Google Workspace: connect everyday work with explicit scopesTool & integration · Everyday administrationUse the documented Workspace skill route for Gmail, Calendar, Drive, Sheets, Docs, and related account data.
  8. Home Assistant: let Hermes see and control your smart homeTool & integration · Skills, plugins & MCPInstall the official homeassistant plugin to give Hermes smart-home tools and react to entity state changes.
  9. Image generation: create images from a text promptTool & integration · Skills, plugins & MCPPick an image backend such as FAL.ai, OpenAI, OpenRouter, xAI or Krea so the agent can generate images on request.
  10. MCP: connect external tool serversTool & integration · Development & operationsExpose selected tools from a local or remote MCP server to Hermes without building a native tool first.
  11. Slack: bring Hermes into your team workspaceTool & integration · Messaging & the gatewayConnect Hermes to Slack over Socket Mode so allowed teammates can message it in DMs, channels and threads.
  12. Subagent delegation: split big jobs across parallel child agentsTool & integration · Automation & schedulingUse the delegate_task tool to hand pieces of work to isolated child agents that run in parallel and report back.
  13. Telegram: reach Hermes from a private bot conversationTool & integration · Everyday administrationUse Telegram as a conversation and delivery surface while keeping bot credentials and allowed users explicitly controlled.
  14. Terminal backends: choose where the agent's commands runTool & integration · Running & deployingRun the agent's shell commands locally, in Docker, on a remote host over SSH, or in cloud sandboxes like Modal, Daytona and Vercel Sandbox.