AetherAI

Scroll down...

01

One workspace. Your choice of AI.

Chat, work on projects and connect tools in AetherAI. Choose a model on your computer or a cloud provider for each task.

Windows, macOS, Linux · Models and tools in one desktop app
02

You choose where requests go.

Connect your own API key to OpenRouter, Groq, Gemini, Cerebras or SambaNova. Messages and attached context go to the provider you select.

Providers set their own limits and prices · Ollama Cloud is a separate connection
03

Tools with your permission.

MCP connects tools; Markdown Skills add instructions. The built-in Workspace reads project text files. Require approval for MCP calls or disable them in planning mode.

You choose the connections and permissions · Skills are instructions, not executable plugins
04

See the work. Stay in control.

For suitable tasks, a coordinator assigns up to two specialists. See their models, tasks, status and drafts before the main model combines the answer. Stop cancels active requests.

Extra agents make extra requests · They do not guarantee a faster answer
How it works

02 / INSIDE THE APP

One workspace. More possibilities.

Chat, work on projects and connect tools in AetherAI. Choose a model on your computer or a cloud provider for each task.

AetherAIFEATURE OVERVIEW
ON YOUR COMPUTER

Start with one model.

Windows Quick setup downloads the engine and Qwen 1.5B. On macOS and Linux, install Ollama and choose a model.

Qwen 2.5 · 1.5BLocal
OllamaWindows, macOS, Linux

Models download separately. Larger models need more memory.

AetherAI

READY FOR YOUR FIRST IDEA?

Download AetherAI

Choose your system and install AetherAI.

Version 1.25.2

For local models, Windows x64 offers Quick setup with a built-in engine; macOS and Linux use Ollama. Cloud models require a separate provider connection.
macOS builds are unsigned and not notarized by Apple.

View on GitHub ↗Read the documentation ↗All releases ↗

A FEW MORE QUESTIONS

Before you start.

Do I need a subscription?

Local chat is free. Cloud providers have their own free limits and paid plans. An API key is required for cloud models.

Do I need a powerful GPU?

Small models can run on a CPU. Speed and model size depend on your hardware and available memory. Cloud models do not need a local GPU.

What does Quick setup install?

On Windows x64, it downloads llama.cpp and Qwen 2.5 1.5B: about 1.14 GB, plus Microsoft Visual C++ components if needed. macOS and Linux use Ollama for local models.

How do I install on Linux or Mac?

Linux: install the .deb on Ubuntu/Debian, or make the AppImage executable and run it (FUSE may be required). Mac: open the DMG and drag AetherAI to Applications. macOS may require approval in Privacy & Security for the unsigned app.

Where can I report a bug?

Open GitHub Issues and include the app version, model and steps to reproduce. GitHub Issues ↗