AI Runner

A local AI desktop app runs offline chat, voice conversations and image generation on Linux, with a layered canvas and a self-hosted API.

Alternative to:

Screenshot of AI Runner website

AI Runner is a desktop app for people who want an AI companion and an art workspace on their own hardware. Its local chat, voice and image tools work offline without an API key or subscription.

  • Personal companion: Choose a name, personality and voice for a companion that remembers conversations across sessions and changes mood as you talk.
  • Voice conversations: Speak to the companion through speech recognition and hear its replies through text-to-speech; speech recognition supports English.
  • Layered art canvas: Draw, paint and composite images, turn sketches into generated artwork, revise existing images and use inpainting to edit selected areas.
  • Image models: Create images with Stable Diffusion 1.5, SDXL or Z-Image Turbo, with support for LoRA, embeddings, filters and background removal.
  • Self-hosted API: Serve chat, image generation and speech tools to other applications, with Ollama-compatible endpoints and OpenAI-compatible chat completions that support tool calls.

Local LLM chat uses GGUF models through llama.cpp, with Qwen3.5-9B as the default, and can also connect to Ollama. OpenAI and OpenRouter are optional cloud providers. Conversations, memories and companion settings stay on your machine by default; enabling a cloud feature can send data outside it. The app has no telemetry.

AI Runner is free and open source under GPL-3.0. Linux is the primary supported platform. The stated minimum hardware includes 16 GB RAM and an NVIDIA RTX 3060; the default Qwen3.5-9B model uses about 12 GB of VRAM.

Similar to AI Runner