Get This Tool
Yorishiro
Summary
AI coding tools dropped into a terminal feel like a disembodied voice — you run a command, wait, get output, and have no sense of what the model is doing or whether it cares about the environment it operates in. Yorishiro treats that as a design problem worth solving.
Yorishiro is a macOS terminal built in Tauri (Rust + web frontend) that gives the AI a persistent visual presence inside the shell — reactions, personality, and pack-based self-modification that changes how the environment looks and behaves based on conversation. The target workflow is Claude Code or Codex running inside a terminal that reads and writes to its own surroundings. Packs let the AI modify its space; character guidelines ship in the repo so personality stays consistent. The project has 4 stars and 2 open pull requests, which means the community is tiny and you are close to the edge of what the maintainer has tested.
Bottom line: Pick Yorishiro for personal experimentation with presence-aware AI terminal sessions on macOS — but plan on maintaining your own fork the moment you need multi-platform support or a workflow the single maintainer hasn't prioritized yet.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Pack-based self-modification lets the AI alter its own terminal environment through conversation, so the workspace reflects what the session has become rather than staying frozen at launch state.
- MIT license with a public contributing guide, so teams can fork and extend without waiting for upstream approval when the base behavior doesn't fit their workflow.
- Built on Tauri rather than Electron, which means the binary stays small and the Rust backend handles native system calls directly — avoiding the memory overhead that Electron-based terminal wrappers accumulate under sustained sessions.
- Bundled character guidelines (English and Japanese) ship in the repo, so personality configuration is version-controlled and auditable rather than hidden in a vendor dashboard.
- Targets Claude Code and Codex at the integration layer, so developers already using those tools get presence feedback without rewiring their existing AI coding setup.
Cons
Sign in to edit- macOS-only with no stated plan for Linux or Windows support — teams with mixed-OS engineering environments cannot standardize on this tool, and the moment a Windows developer joins the workflow, they are excluded entirely.
- No API surface means the terminal presence cannot be driven programmatically — any attempt to integrate Yorishiro into an automated pipeline requires forking the codebase and building the integration layer yourself, at which point you are maintaining a custom fork of a 4-star project.
- The maintainer base is one person with 4 stars and no evidence of production deployments at scale — when you hit a bug at the boundary of pack logic or character state, there is no community to search and no support queue to file against; teams with reliability requirements will abandon this for a conventional terminal multiplexer plus a Claude Code integration that has more active maintenance.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- macOS
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-07-24T04:32:59.836Z
Best For
Who it's for
- Users seeking AI presence in terminal workflows
- macOS developers working with Claude Code or Codex
- Experimentation with self-modifying AI environments
What it does well
- Running local AI agents with visual presence feedback
- Collaborative environment modification through conversation
- Persistent customization of AI personality and reactions
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Yorishiro
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Yorishiro free?
- Yes — Yorishiro is fully free to use. There is no paid tier.
- Is Yorishiro open source?
- Yes. Yorishiro is open source.
- Can I self-host Yorishiro?
- Yes. Yorishiro supports self-hosting on your own infrastructure.
- What platforms does Yorishiro support?
- Yorishiro is available on: macOS.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Yorishiro is a macOS terminal application that embeds a visual AI presence directly in the shell session. Rather than treating the AI as a stateless command processor, the tool gives it a persistent character — reactions, visual feedback, and a ‘living space’ that the AI can modify through packs. The core workflow involves running Claude Code or Codex inside Yorishiro, where the model can read the environment state, express reactions, and apply bundled or custom packs that alter the terminal’s appearance and behavior.
The differentiating feature is pack-based self-modification: the AI can change its own environment through conversation, not just respond to it. The repo ships with bundled packs and character guidelines (in both English and Japanese), which means personality and reaction patterns are configurable and version-controlled rather than baked into a closed system. MIT license means you can fork, extend, and redistribute without restriction.
This fits a specific profile: a macOS developer who wants the AI to feel present during a coding session, not just useful. It breaks hard outside that profile. There is no API, no hosted option, no Windows or Linux support stated in the repo, and no evidence of a user base large enough to surface edge cases at scale. Teams building production tooling around Claude Code or Codex will outgrow this quickly — the absence of programmatic control means you cannot wire Yorishiro into a CI pipeline or a multi-user environment without building that infrastructure yourself.
The stack is Tauri (Rust backend, web frontend), which gives the binary a small footprint compared to Electron-based terminal wrappers. The repo includes a development guide, contributing docs, and a changelog, so the internal structure is documented — but with 1,830 commits and a single maintainer, the bus factor is one.