The local-first AI workstation
on your machine.

Zatinok is designed to run locally on your device with minimal reliance on cloud services. To make that possible, it bundles the runtimes and tools needed for local AI workflows, including: • A managed llama.cpp runtime (CUDA, Vulkan, and AMD HIP builds) for GPU-accelerated local LLM inference • Voice synthesis (TTS/voice cloning) and a bundled whisper.cpp speech-recognition engine • Image, video, and music generation components and their Python runtimes • Document processing tools such as OCR, PDF utilities, and LibreOffice • GPU acceleration libraries for NVIDIA and AMD hardware Language models themselves are not bundled by default and can be downloaded from within the app's model manager. The larger download size comes from bundling the local inference runtimes, media generation pipelines, and multi-backend acceleration libraries needed for a fully self-contained, offline-capable experience.

The download is already trimmed where it matters most: language models and the large image, video, and music models are not bundled — the app fetches them on first use, so you only download what you actually run. What remains in the base download are the media generation runtimes (audio and vision) with their dependencies, plus the llama.cpp builds for every GPU backend (CUDA, HIP, and Vulkan) so the same package works on NVIDIA and AMD hardware out of the box. Slimmer variants — per-vendor GPU builds, or a chat-and-agents-only edition without the media runtimes — are technically possible and something we're considering for a future release.

Yes. Zatinok supports cloud providers through API keys. You can connect OpenAI, Anthropic, or any OpenAI-compatible endpoint — including self-hosted models, local inference servers, and third-party APIs like Groq, Together, or Mistral — and switch between local and cloud models in the app. This lets you use local models for privacy-sensitive tasks and cloud models when you want additional capability or speed.

Zatinok includes a built-in model manager. Browse the catalog or paste a Hugging Face repo or direct URL, and the app downloads the GGUF file for you — with checksum verification and resumable downloads. Downloaded models run on the bundled llama.cpp runtime, and router mode lets you keep several loaded and switch between them instantly. For cloud models, add an API key for OpenAI, Anthropic, or any OpenAI-compatible endpoint in Settings.

Zatinok is free to use. Zatinok Pro is a one-time purchase that unlocks the agentic features — custom agents, playbooks, scheduled jobs, and the runs inbox with agent analytics. There is no subscription. After purchase you receive a license key by email. Enter it in the app under Settings → Preferences → License. One key can be activated on up to 5 devices at the same time. If you replace a computer or hit the limit, you can free up a slot on the Manage Devices page on this website — no need to contact support. Your license and existing keys from ShadowAI continue to work in Zatinok.

No. Zatinok does not include telemetry, analytics, or user tracking. The app periodically contacts our update server to check whether a new version is available. No personal data or usage information is sent — only your current app version. Automatic update checks can be turned off in Settings. If you have Discord open, Zatinok will connect to Discord's local Rich Presence IPC to display your activity status (e.g. "Using Zatinok"). This connection is local — no data is sent to our servers. You can disable this in Settings if you prefer. Aside from the above, your data stays on your device unless you choose to connect to a cloud provider through your own API key. If you encounter issues, please contact us directly so we can investigate.

No. Zatinok runs on CPU-only systems, though a GPU substantially improves performance for local inference, voice, and media generation. Supported backends: CUDA (NVIDIA), HIP/ROCm (AMD), Vulkan (cross-vendor), and DirectML (AMD/Intel integrated). The app detects your hardware automatically and picks the best one — you can override it in Settings. No GPU? You can still use the app fully through cloud providers.

Zatinok can run multiple local AI components simultaneously — a local LLM loaded in memory via llama.cpp, the audio and speech-recognition runtimes, and the vision runtime for image or video generation. Each of these carries its own memory footprint, which adds up quickly. With 16 GB of RAM, you can run all features comfortably at the same time. With 8 GB, the app still works well for chat and agents, but running image or video generation alongside a loaded LLM may cause memory pressure. For media generation (image, video, music), GPU VRAM is just as important as system RAM. 6 GB of VRAM is a practical minimum for image generation; 8 GB or more is recommended for video.