Yorishiro: Giving Claude Code a Visual Presence

Developer sktkkoo released Yorishiro, a macOS application that gives Claude Code a visual presence by mapping the AI agent's internal state to on-screen character expressions, lighting, and UI effects via a self-referencing Model Context Protocol (MCP). The tool turns abstract prompt engineering into tangible environmental notifications, such as happy expressions and fireworks on a successful git push or a sad look on crashes, and supports extension hot reloading for a self-modifiable terminal experience.

Yorishiro: Giving Claude Code a Visual Presence The core idea is to map the agent's internal state to visual cues. I've implemented "Aura" a white light that flashes to indicate what the LLM is focusing on before it replies and environment triggers. For example, if a git push succeeds, the character shows a happy expression and fireworks trigger; if the agent hits a crash or an API error, the character looks sad. Technically, this works via a self-referencing MCP /en/tags/mcp/ Model Context Protocol . The AI agents actually control the lighting, the character's body, the scene, and the UI effects in real-time. I've also added extension support with hot reloading, making it a self-modifiable terminal similar to how Emacs operates. If you want to test this AI workflow on macOS: brew install --cask sktkkoo/yorishiro/yorishiro It turns the abstract process of prompt engineering and agent execution into something tangible. Instead of staring at a blinking cursor while waiting for a complex task to finish, you get environmental notifications when the agent is waiting for your approval. Next AGI and the End of Intelligence Scarcity → /en/threads/3528/