Linux desktop AI · Version 0.4.3 · By Lorelei Noble · Updated September 22, 2026
Run local AI on Linux with Arynwood MCP
Arynwood MCP is an all-in-one local AI workspace for your Linux desktop. It combines a chat interface, model management, knowledge search and creative-tool connections. The desktop package contains the interface and backend; you install the models and supporting services separately.
This guide summarizes the v0.4.3 release and its versioned installation documentation. It is a setup checklist. For measured CPU and GPU speeds, see Local AI without a GPU.
What hardware do you need?
| Component | Requirement |
|---|---|
| Operating system | Linux x86_64. AppImage or Debian/Ubuntu .deb. Windows and macOS are not supported. |
| Memory | 16 GB RAM minimum in the project documentation; model size affects memory use. |
| Storage | At least 20 GB free, plus space for additional models and generated media. |
| Chat GPU | Optional. Ollama can run chat on a CPU, with slower responses. Measured CPU speeds. |
| Creative GPU tools | NVIDIA GPU required for the documented GPU services; at least 12 GB VRAM is the project’s practical recommendation. Heavy services compete for VRAM. |
Check the versioned platform requirements before choosing which services to run.
Start with one local chat workflow
- Choose the package. Open the v0.4.3 release and download the x86_64 AppImage or .deb. Compare its SHA-256 checksum with the release’s SHA256SUMS.txt.
- Install and launch. Make the AppImage executable and run it, or install the .deb using your package manager. Follow the installation instructions, including the GStreamer packages needed for .deb audio and video.
- Install Ollama and download models. Ollama is not bundled. Use the versioned quick start to configure the models used by the personas. Match model size to your available RAM and GPU memory.
- Verify chat first. Check that Ollama is reachable, select an installed model and send a message. Resolve model-loading or service errors before adding creative tools.
- Add knowledge search when needed. Install Qdrant and the Ollama embedding model specified in the knowledge-base instructions. These support retrieval from your documents and memory.
Which features need extra setup?
- Image generation: A1111 runs as a separate service. The design canvas can connect to it once configured.
- Music and audio: install the MusicStudio sidecars and any models required by the specific feature. Models are not included in the desktop download.
- MCP and video editing: Kdenlive integration needs the compatible editor, a running MCP server and local server configuration. A fresh app install does not automatically connect these.
- Social publishing: requires network access and platform accounts. Remote model endpoints also send requests to the chosen service.
What is missing from the packaged alpha?
v0.4.3 does not include IRC or end-to-end encrypted messaging. LoRA training, script-based GPU tools such as Whisper and SadTalker, the project file browser and useful automatic project-tree context require a source checkout. The release download alone does not provide them.
The installation guide distinguishes script-based tools from separate HTTP services such as A1111. Consult the troubleshooting guide if a service is unavailable.
Is local AI private and offline?
Ollama inference runs on the machine hosting the model. For a local workflow, use local endpoints and installed models. Downloads, web search, remote endpoints and social publishing need network access. Review enabled integrations before using sensitive material; “local-first” describes a deployment choice, not a promise that every feature works offline.
Want help setting this up?
I offer paid local AI setup and workflow integration. Start with your hardware and one useful outcome, then scope the services needed to get there.