43 results for “memory”

  1. Can Hermes search my old conversations?FAQ · Memory & contextYes. Every CLI and messaging session is stored in a SQLite database at ~/.hermes/state.db with full-text search, and the agent has a session_search tool to find and scroll…
  2. Can Hermes work with an Obsidian vault or my own markdown notes?FAQ · Research & knowledge workYes. The bundled Obsidian skill lets the agent read, search, create and edit notes and add wikilinks. Set `OBSIDIAN_VAULT_PATH` in your `.env` to the vault's folder (otherwise…
  3. Can I move over from OpenClaw?FAQ · Getting startedYes. hermes setup detects ~/.openclaw and offers to migrate, or you can run hermes claw migrate anytime. Add --dry-run to preview, or --preset user-data to skip infrastructure…
  4. Can I run Hermes with a local model, and which models fit my GPU or Mac?FAQ · Models, providers & costYes. The easiest route is Local Models: in Hermes Desktop open Settings > Providers > Local Models, or in a terminal run `hermes model` and choose Local models. Hermes installs…
  5. Can I use Hermes inside VS Code, Zed or JetBrains?FAQ · Running & deployingYes, through ACP (Agent Client Protocol). `hermes acp` runs Hermes as an ACP server over stdio, and editors can show its chat, tool activity, file diffs, terminal commands and…
  6. Does Hermes write its own skills or plugins, and how do I make it save a lesson reliably?FAQ · Skills, plugins & MCPYes. With its `skill_manage` tool the agent creates, updates and deletes skills, for example after working out a multi-step workflow, finding a fix after dead ends, or being…
  7. Hermes seems less capable than before. What should I check?FAQ · TroubleshootingThe docs give a checklist. First confirm the model with `/status` or `/model`: a `/model` switch is session-only by default, and model changes from the dashboard apply only to…
  8. How do I connect Hermes to Telegram, and can I run separate bots there?FAQ · Messaging & the gatewayCreate a bot with @BotFather to get a token, then run `hermes gateway setup` and choose Telegram. It asks for the token and your allowed user IDs. Or add `TELEGRAM_BOT_TOKEN`…
  9. How do I continue a previous conversation?FAQ · Memory & contextUse hermes --continue (or -c) to resume the most recent CLI session; in each terminal it prefers that terminal's own last session. Use hermes --resume <id or title> for a…
  10. How do I hand Hermes a file, a git diff or a web page in my message?FAQ · Memory & contextUse an @ reference. `@file:path/to/file.py` injects a file (append `:10-25` for a line range), `@folder:` a directory listing, `@diff` and `@staged` your git changes, `@git:5`…
  11. How do I switch from Claude Code or Codex to Hermes?FAQ · Getting startedStart with `hermes import-agent`. It auto-detects `~/.claude` or `~/.codex`, or you can name one: `hermes import-agent claude-code` or `hermes import-agent codex`. It shows a…
  12. Is Hermes good for coding, and can it replace Claude Code or Codex?FAQ · ComparisonsIt's a capable coding agent: it reads, edits and runs code in your projects, follows AGENTS.md or CLAUDE.md, gets real type errors from bundled language servers after each…
  13. Is Telegram or Discord easier to connect, and do they get the same features?FAQ · Messaging & the gatewayTelegram is usually the quickest: one token from @BotFather, and Hermes Desktop can even create the bot from a QR code. Discord needs an application in the developer portal…
  14. Is there a web interface for managing Hermes?FAQ · Running & deployingYes. `hermes dashboard` starts a local web server and opens `http://127.0.0.1:9119`. From there you can manage config, API keys, MCP servers, messaging pairing, webhooks, the…
  15. My local model server errors out or goes quiet on long chats. What’s wrong?FAQ · TroubleshootingUsually the context length Hermes assumes doesn't match the server. Set `model.context_length`, or a per-model `context_length` under `providers`, to the window your server…
  16. What are AGENTS.md and other context files?FAQ · Memory & contextContext files are project instructions Hermes loads automatically. It looks for .hermes.md or HERMES.md, AGENTS.override.md, AGENTS.md, CLAUDE.md and .cursorrules, and loads…
  17. 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…
  18. 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…
  19. What is Hermes Cloud, how is it priced, and is storage persistent?FAQ · Running & deployingHermes Cloud is Nous Research's hosted Hermes Agent: an always-on agent on a dedicated cloud instance with its own workspace and dashboard, managed from the agents page in Nous…
  20. When should I use the Kanban board instead of subagents?FAQ · Automation & scheduling`delegate_task` works like a function call: the parent waits for an anonymous child and gets a summary back. Kanban is a durable work queue in `~/.hermes/kanban.db` where named…