AIRI

license

MIT(OSI)

source

public(moeru-ai/airi)

core-gated

ungated(no enterprise or ee path in the repository root and no paid tier described in the README)

MIT, an OSI licence, with the full source public and the shipped code in this repository. The LICENSE body was read in full: the stock MIT text, with no appended condition. No enterprise or ee path in the repository root and no paid tier described in the readme.

• https://raw.githubusercontent.com/moeru-ai/airi/main/LICENSE recorded 2026-08-31

  LICENSE body, read in full: the stock MIT licence text carrying a 2024-PRESENT copyright line for Neko Ayaka, with no appended term or additional condition.

• https://raw.githubusercontent.com/moeru-ai/airi/main/README.md recorded 2026-08-31

  README, read for the distribution and gating question: it documents building the browser, desktop and mobile stages from this repository and names no enterprise, paid or licence-gated build.

Banded on stars, because the product has no bridged distribution channel: it ships as browser, desktop and mobile builds, and the npm package named `airi` is an unrelated stub at version 0.0.1 with no repository field, so it is not declared here. 48,642 stargazers places it at level 3, and the instrument caps the band at 3. Stars measure attention rather than use, so confidence is low.

• https://api.github.com/repos/moeru-ai/airi recorded 2026-08-31

  Repo metadata for moeru-ai/airi: stargazers_count 48642, archived false, pushed_at 2026-08-31.

Scored 3 in the companion front-end class that sillytavern occupies. Its modality breadth - voice in and out, vision, three form factors - is real and is what puts it at the top of that band, but it organizes a character conversation rather than providing the retrieval, tool and document surface that places anythingllm and open-webui at 4.

• https://raw.githubusercontent.com/moeru-ai/airi/main/README.md recorded 2026-08-31

  README documents Stage Web, Stage Tamagotchi and Stage Pocket as browser, desktop and mobile versions, a provider matrix powered by the xsAI library, and speech, vision, memory and MCP capabilities across the sub-projects born from the platform.