# Capsize-Games/airunner

Offline inference engine for art, real-time voice conversations, LLM powered chatbots and automated workflows

Repository: https://github.com/Capsize-Games/airunner
Canonical: https://ross.abutalabs.com/products/airunner
Homepage: https://airunner.capsizegames.com
Language: Python
License: NOASSERTION
License Family: other
Topics: ai, ai-art, art, asset-generator, python, stable-diffusion, deep-learning, image-generation, text-to-image, text-to-speech, multimodal, chatbot, speech-to-text, desktop-app, privacy, pyside6, mistral, text-to-speech-app, self-hosted, pygame
Last push: 2026-08-23T14:54:48+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 48, longevity 90
- inputs: {"age_days": 1261, "days_push": 10, "days_rel": 265, "gap_med": 0.0, "n_releases_24m": 167}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1314, forks 102 (observed 2026-08-28T04:04:20.424577+00:00)

## What it is
AI Runner is a privacy-focused desktop application for running local AI models offline, combining an AI chat companion with voice conversation, long-term memory, and a layered canvas for Stable Diffusion image generation. It bundles LLM, TTS, STT, and image generation models in a PySide6 GUI that runs entirely on the user's own hardware.

## Use cases
- run stable diffusion locally to generate images
- chat with a private offline AI companion
- have real-time voice conversations with a local LLM
- convert sketches to images with AI on a drawing canvas
- run text-to-speech and speech-to-text offline
- build a chatbot with long-term memory without cloud APIs
- generate AI art without an internet connection or subscription

## When to choose
- you want fully offline, private AI chat and image generation on your own GPU
- you need a combined art canvas and AI companion in one desktop app
- you want voice-based interaction with a local LLM including TTS and STT
- you prefer no API keys, subscriptions, or telemetry

## When to avoid
- you need cloud-scale or API-based model serving
- you lack a capable GPU or local hardware for running models
- you need a headless server or programmatic API rather than a GUI
- you require permissively licensed code for commercial embedding, since it is GPLv3

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, stable-diffusion, tts, speech-recognition, rag, chatbot, image-processing, agent-framework
- domain: artificial-intelligence, large-language-models, image-processing, speech-processing, chatbots, privacy, self-hosted, desktop-applications
- platform: python, windows
- tags: offline-ai, ai-companion, local-llm, text-to-image, pyside6, voice-chat, layered-canvas, generative-art, desktop, linux, macos, gpu

## Member repositories
- Capsize-Games/airunner (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:20.424577+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:48:44.135445+00:00, confidence not recorded.
  - readme: https://github.com/Capsize-Games/airunner (fetched 2026-08-28T04:04:20.424577+00:00, sha 5e915731b1cc)
  - registry_pypi: https://pypi.org/pypi/airunner/json (fetched 2026-08-29T12:07:17.885237+00:00, sha b4eb58457531)
- Data as of 2026-08-30T08:39:29.467469+00:00.