Nous Research Ships Hands-Free 'Hey Hermes' Wake Word to Its 175K-Star Agent
Hermes Agent adds always-on, fully local 'Hey Hermes' wake word detection across CLI, TUI, and desktop app
- Wake word shipped: Hermes Agent now supports hands-free "Hey Hermes" activation across CLI, TUI, and desktop app.
- Fully local: Detection runs entirely on-device; no audio leaves your machine until you speak a command.
- Three engines: openWakeWord (default, bundled model), sherpa (open-vocabulary, zero training), and Porcupine (custom .ppn files).
- Multi-profile routing: With the sherpa engine, saying "hey coder" or "hey trader" live-switches to the matching profile -- one listener, any profile.
- Off by default: Enable with
/wake onin CLI or the ear icon in the desktop app; persists toconfig.yamlautomatically. - Free and open-source: MIT licensed; available now at hermes-agent.nousresearch.com.
Hermes Agent now supports wake words. Nous Research shipped the feature across the CLI, TUI, and desktop app, letting you trigger the agent hands-free by saying "Hey Hermes." The entire detection pipeline runs on-device.
What shipped
With wake word enabled, Hermes listens in the background for a spoken trigger phrase. Say it, and Hermes starts a fresh session, opens the microphone, captures your command through the normal voice pipeline, and responds. The flow mirrors "Hey Siri" or "Alexa." Detection runs locally; no audio leaves your machine until you speak a command. The feature is off by default.
Three detection engines
The feature ships with three backends you can swap in config:
- openWakeWord (default) — free, local ONNX models. Bundles a "hey hermes" model; also supports
hey_jarvis,alexa,hey_mycroft, and custom models. - sherpa — open vocabulary: detects any typed phrase with zero training. A small English model downloads automatically on first use at roughly 13 MB.
- Porcupine — the Picovoice engine; built-in keywords plus custom
.ppnfiles. Requires aPORCUPINE_ACCESS_KEYand has a free tier.
Custom phrases without training
Most wake word systems require you to train a model on a custom phrase, which can take hours of compute. The sherpa engine skips that entirely. Type any phrase and it tokenizes at runtime — no training data, no waiting.