Alex Finn tests Hermes Bot, a multi-agent modeA multi-agent system contains multiple AI agents that interact, coordinate, divide work, or influence one another while pursuing tasks. that turns saved Hermes profiles into named agents with their own models, tools and context. The agents can communicate with one another, divide work and operate through a shared interface.
Alex Finn says Hermes Bot's main advantage is flexibility: users can choose providers, run local modelsA local model runs on computing infrastructure controlled directly by the user rather than only through a remote model service., customize tools and let agents work directly on local files or Git repositoriesRepository context is the relevant source, configuration, history, documentation, dependencies, and worktree state needed to understand a software task.. Splitting work among specialized agentsA specialized AI agent is configured for a focused role with task-specific context, tools, models, and permissions. also reduces the context overload that weakens a single oversized assistantContext engineering designs the information, instructions, memory, and tool state an AI receives so it can perform a task reliably..
Alex Finn finds Grok Bot more polished for visible orchestration, isolated virtual computers and mobile use, but also more expensive and tied to a narrower model stack. Hermes Bot is the stronger fit for power users who value control, while Grok Bot remains easier for general collaborative work.
Watch on YouTube
