Amadeus

Meet Amadeus

Local models: NVIDIA CUDA cu124 · AMD ROCm / Windows (experimental) · Apple MPS Quick start · Website & resources · Installation profiles · Contribute

Amadeus is a real-time multimodal desktop agent that brings voice, character presence, and Agent work into one interface. Speak or type naturally, delegate tasks to specialized Providers, and stay involved through visible progress, permission requests, and controls to resume or take over.

The desktop app and Host run locally, with remote services or local inference selected through model configuration. Character packs are optional: Chat and Work remain available without them.

What you can do

Getting started

1. 1

   Dependencies are grouped into four capability tiers. Start with the minimal T1 installation, then add the tiers you need. A tier is a recommended install preset: each one is a strict superset of the one below it, and the extras themselves encode that (vad includes voice; every local-<build> includes vad). Platforms are not capped; the table below only recommends a tier and build per platform. Terminology is fixed by the tier and build taxonomy.

2. 2

   All profiles use uv and Python 3.12; CI pins uv 0.12.8.

3. 3

   Linux users should start with Linux below.

4. 4

   T3 and T4 need a Torch build, selected independently of the tier: torch-cpu for T3, or one of local-cpu, local-cu124, local-cu128, local-mps, and local-rocm for T4. The default T1 and T2 presets stay Torch-free; optional extras such as rag with torch-cpu may still add Torch. Longer commands that also name voice and vad remain valid and select the same environment. Optional character RAG adds local embedding/Torch dependencies to whichever command you use.