# Hermes Agent tools and integrations

> Capabilities, integrations, providers and surfaces of Hermes Agent, each explained from the official docs.

Canonical: https://hermeswatcher.com/tools

## Capability

- [Skills: reusable procedures for repeated work](https://hermeswatcher.com/tools/skills.md): Package a successful procedure so Hermes can load the relevant instructions when a similar task returns.
- [Plugins: add tools and lifecycle behavior](https://hermeswatcher.com/tools/plugins.md): Extend Hermes with custom tools, hooks, and integrations when instructions alone cannot supply the needed capability.
- [Scheduled tasks: automate a proven run](https://hermeswatcher.com/tools/scheduling.md): Run bounded tasks on a schedule and retain separate evidence of execution, useful output, and delivery.
- [Persistent memory: retain compact working knowledge](https://hermeswatcher.com/tools/memory.md): Retain stable preferences and environment facts across sessions while keeping detailed evidence in durable project records.
- [Context files: give a project durable instructions](https://hermeswatcher.com/tools/context-files.md): Keep project rules, conventions, and operating boundaries in files that Hermes can discover from the working directory.
- [Browser tools: interact with pages when retrieval is insufficient](https://hermeswatcher.com/tools/browser-tools.md): Use a configured browser backend for navigation, visible page interaction, forms, and tasks requiring an authenticated session.
- [Web search and extraction: collect usable source evidence](https://hermeswatcher.com/tools/web-search.md): Discover pages and retrieve readable source content with a configured backend, keeping search results distinct from verified evidence.
- [Voice and TTS: spoken replies and voice-note transcription](https://hermeswatcher.com/tools/voice-tts.md): Choose a text-to-speech and speech-to-text provider so Hermes can talk back and understand voice messages.
- [Subagent delegation: split big jobs across parallel child agents](https://hermeswatcher.com/tools/subagent-delegation.md): Use the delegate_task tool to hand pieces of work to isolated child agents that run in parallel and report back.
- [Code execution: let the agent script multi-step tool work](https://hermeswatcher.com/tools/code-execution.md): The execute_code tool lets Hermes write and run a Python script that calls its own tools, collapsing many steps into one.
- [Checkpoints and rollback: undo the agent's file changes](https://hermeswatcher.com/tools/checkpoints-rollback.md): Snapshot your working directory before Hermes edits files, then preview or restore earlier states with /rollback.
- [Command approvals: decide what the agent may run unattended](https://hermeswatcher.com/tools/approvals-security.md): Control how Hermes handles dangerous shell commands with smart, manual or off approval modes, deny patterns and a hardline blocklist.
- [Terminal backends: choose where the agent's commands run](https://hermeswatcher.com/tools/terminal-backends.md): Run the agent's shell commands locally, in Docker, on a remote host over SSH, or in cloud sandboxes like Modal, Daytona and Vercel Sandbox.

## Integration

- [MCP: connect external tool servers](https://hermeswatcher.com/tools/mcp.md): Expose selected tools from a local or remote MCP server to Hermes without building a native tool first.
- [Telegram: reach Hermes from a private bot conversation](https://hermeswatcher.com/tools/telegram.md): Use Telegram as a conversation and delivery surface while keeping bot credentials and allowed users explicitly controlled.
- [Discord: keep agent conversation scoped to the right people](https://hermeswatcher.com/tools/discord.md): Connect Hermes to direct messages or server channels with deliberate mention rules, authorization, and session boundaries.
- [GitHub: inspect repositories before automating changes](https://hermeswatcher.com/tools/github.md): Build repository research and review workflows through documented GitHub CLI or separately configured MCP routes.
- [Google Workspace: connect everyday work with explicit scopes](https://hermeswatcher.com/tools/google-workspace.md): Use the documented Workspace skill route for Gmail, Calendar, Drive, Sheets, Docs, and related account data.
- [Home Assistant: let Hermes see and control your smart home](https://hermeswatcher.com/tools/home-assistant.md): Install the official homeassistant plugin to give Hermes smart-home tools and react to entity state changes.
- [API server: use Hermes from any OpenAI-compatible client](https://hermeswatcher.com/tools/api-server.md): Expose Hermes as an OpenAI-compatible HTTP endpoint so chat frontends and scripts can talk to your agent.
- [IDE integration (ACP): run Hermes inside your code editor](https://hermeswatcher.com/tools/ide-integration-acp.md): Start Hermes in Agent Client Protocol mode so editors like VS Code, Zed and JetBrains IDEs can use it as a coding agent.

## Provider setup

- [Models and providers: configure the actual inference route](https://hermeswatcher.com/tools/models.md): Understand which model handles conversation and which auxiliary models handle supporting tasks before diagnosing quality or cost.
- [Image generation: create images from a text prompt](https://hermeswatcher.com/tools/image-generation.md): Pick an image backend such as FAL.ai, OpenAI, OpenRouter, xAI or Krea so the agent can generate images on request.
- [External memory providers: deeper long-term recall](https://hermeswatcher.com/tools/memory-providers.md): Add one external memory backend, such as Honcho, Mem0, Hindsight or Supermemory, on top of Hermes's built-in memory.
- [Fallback providers: keep working when your main model fails](https://hermeswatcher.com/tools/fallback-providers.md): Define a chain of backup model providers that Hermes switches to on rate limits, outages or auth errors.

## Deployment

- [Deployment: separate the agent host from its execution sandbox](https://hermeswatcher.com/tools/deployment.md): Understand the difference between running Hermes in a container and using a container only for terminal commands.

## Surface

- [CLI: run bounded tasks and inspect the working environment](https://hermeswatcher.com/tools/cli.md): Use the terminal interface for interactive work, bounded single queries, explicit tool selection, and resumable sessions.
- [Desktop: manage conversations and inspect artifacts visually](https://hermeswatcher.com/tools/desktop.md): Use the native desktop interface to work with the same Hermes core, sessions, configuration, skills, and memory.

## Messaging platform

- [Slack: bring Hermes into your team workspace](https://hermeswatcher.com/tools/slack.md): Connect Hermes to Slack over Socket Mode so allowed teammates can message it in DMs, channels and threads.
- [WhatsApp: chat with Hermes from your phone](https://hermeswatcher.com/tools/whatsapp.md): Link Hermes to WhatsApp as a linked device through a bundled Node.js bridge, in bot or self-chat mode.
- [Signal: a private, end-to-end encrypted channel to your agent](https://hermeswatcher.com/tools/signal.md): Talk to Hermes over Signal by linking signal-cli as a secondary device and pointing the gateway at its local HTTP daemon.
- [Email gateway: give Hermes its own inbox](https://hermeswatcher.com/tools/email-gateway.md): Let Hermes read a dedicated mailbox over IMAP and reply over SMTP, with sender authentication on by default.

---

HermesWatcher is an independent guide. It is not affiliated with or endorsed by Nous Research. The [official Hermes Agent documentation](https://hermes-agent.nousresearch.com/docs) and [repository](https://github.com/NousResearch/hermes-agent) from Nous Research are the authority; each page here lists the official sources it was written from. If this site and the official docs disagree, trust the official docs. Index for agents: https://hermeswatcher.com/llms.txt