42 results for “rate limit”

  1. Is there a usage or rate limit, and can I tune how Hermes retries?FAQ · Models, providers & costHermes itself has no usage cap; limits come from your model provider or plan. `/usage` shows token use and, when the provider reports it, remaining quota, and `hermes usage`…
  2. What happens when my model provider goes down or rate-limits me?FAQ · Models, providers & costHermes has layers of resilience. A credential pool, meaning several keys for the same provider, is tried first. Then a fallback chain switches to a different provider and model…
  3. Hermes Agent rate limits and provider errorsTroubleshooting · Models, providers & costHow to read 429s, quota errors, auth failures and stream errors from your model provider, and how retries, credential pools and fallback providers can keep Hermes working.
  4. How much can Hermes remember? Is there a limit?FAQ · Memory & contextYes, built-in memory is deliberately small. MEMORY.md is capped at 2,200 characters (about 800 tokens) and USER.md at 1,375 characters (about 500 tokens). The limits are…
  5. 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.
  6. Credential poolGlossarySeveral API keys for the same provider that Hermes rotates between when one hits a rate limit or quota.
  7. Hermes Agent for research that keeps its sourcesGuide · Research & knowledge workSeparate discovery, factual extraction and editorial judgment so a useful summary remains traceable.
  8. Hermes Agent MCP tool missing or failingTroubleshooting · Skills, plugins & MCPSeparate discovery, connection, authentication and operation failures using one known read-only request.
  9. Hermes Agent scheduled job didn't runTroubleshooting · Automation & schedulingSeparate a stopped scheduler, an unwritable store and a failed job before recreating the schedule.
  10. Hermes Agent stuck in a tool loopTroubleshooting · Automation & schedulingHow to stop a Hermes turn that keeps calling tools or seems frozen, and the documented limits and settings that prevent it happening again.
  11. 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.
  12. How to choose a model for Hermes AgentGuide · Models, providers & costSeparate model selection, provider access and tool configuration, then compare them using a representative task.
  13. How to set up Hermes Agent on iMessage with PhotonGuide · Messaging & the gatewayConnect iMessage through Photon's hosted service without a Mac relay. Set access controls and understand shared-line and incoming-attachment limits.
  14. GitHub: inspect repositories before automating changesTool & integration · Development & operationsBuild repository research and review workflows through documented GitHub CLI or separately configured MCP routes.
  15. Is Hermes Agent free, and how do I get the free models?FAQ · Getting startedYes. The software itself is free and open source under the MIT license. What you pay for is the AI model behind it: usage fees from whichever provider you connect, such as…
  16. Build a useful GitHub issue reviewWorkflow · Development & operationsTurn a bounded set of repository issues into a source-linked review with suggested next steps.
  17. Collect content ideas without losing the evidenceWorkflow · Content & creativeMonitor a focused topic and create a ranked queue of source-backed ideas with distinct editorial angles.
  18. Wake up to a useful research briefingWorkflow · Research & knowledge workTurn a defined set of sources into a short, dated briefing with evidence and a clear delivery check.
  19. A software consultancy builds a private Slack assistant that answers questions about the companyCase study · Business operationsEchobind wrote up a Hermes Slack bot that runs on a small private server and answers questions about the company from a condensed summary and a folder of scraped knowledge pages. The write-up is useful mainly for the configuration problems it records, including one where a default setting quietly overrode the Slack tool restrictions.
  20. Hermes Agent forgets things mid-conversationTroubleshooting · Memory & contextWhy a long Hermes session can lose earlier details after context compression, and how to keep the important parts in view.