Features
Explore the powerful features of Hermes Agent.
{ “label”: “Features”, “position”: 4, “link”: { “type”: “generated-index”, “description”: “Explore the powerful features of Hermes Agent.” } }
In this section
- Features Overview
- Tools & Toolsets
Overview of Hermes Agent's tools — what's available, how toolsets work, and terminal backends
- Nous Tool Gateway
Route web search, image generation, text-to-speech, and browser automation through your Nous subscription — no extra API keys needed
- Skills System
On-demand knowledge documents — progressive disclosure, agent-managed skills, and the Skills Hub
- Persistent Memory
How Hermes Agent remembers across sessions — MEMORY.md, USER.md, and session search
- MCP (Model Context Protocol)
Connect Hermes Agent to external tool servers via MCP — and control exactly which MCP tools Hermes loads
- Memory Providers
External memory provider plugins — Honcho, OpenViking, Mem0, Hindsight, Holographic, RetainDB, ByteRover, Supermemory
- Browser Automation
Control browsers with multiple providers, local Chrome via CDP, or cloud browsers for web interaction, form filling, scraping, and more.
- Scheduled Tasks (Cron)
Schedule automated tasks with natural language, manage them with one cron tool, and attach one or more skills
- Event Hooks
Run custom code at key lifecycle points — log activity, send alerts, post to webhooks
- Image Generation
Generate images via FAL.ai — 8 models including FLUX 2, GPT-Image, Nano Banana Pro, Ideogram, Recraft V4 Pro, and more, selectable via `hermes tools`.
- Provider Routing
Configure OpenRouter provider preferences to optimize for cost, speed, or quality.
- Subagent Delegation
Spawn isolated child agents for parallel workstreams with delegate_task
- Vision & Image Paste
Paste images from your clipboard into the Hermes CLI for multimodal vision analysis.
- Code Execution
Programmatic Python execution with RPC tool access — collapse multi-step workflows into a single turn
- Context Files
Project context files — .hermes.md, AGENTS.md, CLAUDE.md, global SOUL.md, and .cursorrules — automatically injected into every conversation
- Fallback Providers
Configure automatic failover to backup LLM providers when your primary model is unavailable.
- Context References
Inline @-syntax for attaching files, folders, git diffs, and URLs directly into your messages
- Credential Pools
Pool multiple API keys or OAuth tokens per provider for automatic rotation and rate limit recovery.
- Personality & SOUL.md
Customize Hermes Agent's personality with a global SOUL.md, built-in personalities, and custom persona definitions
- Voice & TTS
Text-to-speech and voice message transcription across all platforms
- Skins & Themes
Customize the Hermes CLI with built-in and user-defined skins
- Voice Mode
Real-time voice conversations with Hermes Agent — CLI, Telegram, Discord (DMs, text channels, and voice channels)
- ACP Editor Integration
Use Hermes Agent inside ACP-compatible editors such as VS Code, Zed, and JetBrains
- Plugins
Extend Hermes with custom tools, hooks, and integrations via the plugin system
- Batch Processing
Generate agent trajectories at scale — parallel processing, checkpointing, and toolset distributions
- RL Training
Reinforcement learning on agent behaviors with Tinker-Atropos — environment discovery, training, and evaluation
- API Server
Expose hermes-agent as an OpenAI-compatible API for any frontend
- Web Dashboard
Browser-based dashboard for managing configuration, API keys, sessions, logs, analytics, cron jobs, and skills
- Dashboard Plugins
Build custom tabs and extensions for the Hermes web dashboard
- Honcho Memory
AI-native persistent memory via Honcho — dialectic reasoning, multi-agent user modeling, and deep personalization