Alex Finn demonstrates Hermes Agent's bot mode, where separate profiles can use different models, memories and tools. He organizes those profiles by model strengths rather than creating one bot per job title, and shows a desktop flow for setting up locally hosted models that match the available hardwareOn-device inference runs an AI model directly on a user's phone, computer or edge device instead of sending each request to a cloud service..
The video then tours a movable, screen-aware HUD, voice interaction, a wake-word command and a subagent interface that exposes each worker's activity and model choiceAI agent observability makes an agent's state, actions, tool use, failures, resource use, and outcomes visible enough to understand and operate it.. These examples show how the creator uses multiple agents togetherAgent orchestration coordinates AI agents, tools, people, tasks, state, and control flow so a larger workflow reaches a verified outcome.; they do not establish that every configuration will behave the same way for every user.
Scheduled jobsScheduled AI automation runs an AI-assisted workflow at defined times or recurring intervals without requiring a new manual start for every run. are described as retaining earlier research, reducing repeated workAI agent memory is stored information that an agent can retrieve and use across steps, sessions, or changing contexts. in recurring tasks. The closing comparison explains the creator's preference for Hermes Agent in configurable, multi-model and personal workflows, while using other tools for different kinds of work.
Watch on YouTube
