title: AIRI source guide description: Understand Project AIRI, choose a runtime surface, and trace its character, provider, audio, and service boundaries.
AIRI source guide
Project AIRI is an open-source virtual-character project. Its repository contains browser, desktop, and mobile applications, shared character modules, and separate services.
A character experience combines several systems. A display model supplies the visible character. A generation provider supplies model responses. Speech, hearing, and external integrations have their own requirements.
Open the AIRI showcase for a reader-facing introduction. This wiki explains the source behind that introduction.
A showcase is not an active character session
Architecture cards and workflow descriptions do not prove that a model, microphone, account, or game integration is active. Read capability-boundaries before treating a source capability as a hosted feature.
Choose a reading path
- For a first visit, read capability-boundaries, then workflows. These pages separate what AIRI contains from what a real session needs.
- For development, read architecture, modules, and setup. These pages identify package owners and source-derived commands.
- For providers and character assets, read providers-and-models and character-and-audio. A language model and a display model are different resources.
- For external services, read services-and-integrations, then operations. A browser build does not start every service in the repository.
- For evidence, read provenance. It records the upstream revision and separates source facts from deployment reports.
One project, several surfaces
| Surface | Source location | Main responsibility |
|---|---|---|
| Browser application | apps/stage-web | Vue application and browser-facing routes |
| Desktop ver. | apps/stage-tamagotchi | Electron application, renderer windows, and native integration boundaries |
| Mobile ver. | apps/stage-pocket | Vue application with Capacitor Android and iOS targets |
| Shared stage code | packages/stage-ui, packages/stage-pages | Character modules, state, components, and shared settings pages |
| Hosted backend | server/ | Resource API, authentication, database, and service infrastructure |
| Server channel | packages/server-runtime, packages/server-sdk | A separate communication path for connected runtimes and integrations |
flowchart TD Visitor[Choose a goal] --> Learn[Understand the source] Visitor --> Run[Run a character session] Learn --> Guide[Showcase and wiki] Run --> Surface[Browser, desktop, or mobile] Surface --> Shared[Shared stage modules] Shared --> Provider[Configured generation provider] Shared --> Character[Display model and renderer] Shared --> Audio[Optional hearing and speech] Shared --> Services[Optional external services]
Terms that prevent confusion
A provider connects AIRI to an inference service or local subsystem. An inference model is the model selected through that provider.
A display model is character artwork or a 3D asset. An AIRI card holds character information and module selections. Neither resource supplies language-model inference by itself.
The hosted backend and the server channel are separate systems. Their commands, authentication boundaries, and dependencies are not interchangeable.
Source context
This guide describes upstream revision 3da3cf815490b40521e24b22020954e7959d79b4, reviewed on 2026-09-15. It does not claim a completed deployment or hardware acceptance test.
package.json, lines 1–35: project identity and application commands.apps/stage-web/package.json: browser dependencies and scripts.apps/stage-tamagotchi/package.json: desktop entrypoint and scripts.apps/stage-pocket/package.json: Capacitor targets and shared packages.
Continue with architecture or return to the showcase.