Status: [UNTESTED] Endpoints found: http://127.0.0.1:8787/v1/noul http://127.0.0.1:8787/v1/choice http://127.0.0.1:8787/v1/shared http://127.0.0.1:8787/v1/models/installed http://127.0.0.1:8787/v1/models/activate Source: https://github.com/ILuce/deqio # Deqio **Decisions in. Probabilities out.** Deqio runs fast typed AI decision models behind one consistent local API and a lightweight browser UI. It supports multiple decision engines and lets you switch between installed models without changing your application code. Public decision endpoints stay the same regardless of the active model: ```text POST /v1/noul POST /v1/choice POST /v1/shared ``` ## 1. Installation ### macOS — Apple Silicon Deqio supports both **MLX** and **MPS** on Apple Silicon. 1. Install `uv` if you do not already have it: ```bash curl -LsSf https://astral.sh/uv/install.sh | sh ``` 2. Clone Deqio and enter the project: ```bash git clone https://github.com/ILuce/deqio.git cd deqio ``` 3. Install the project: ```bash uv sync ``` 4. Choose a backend and model: ```bash uv run deqio models setup ``` On a Mac, the installer offers: - `mlx` — recommended for models with native MLX support - `mps` — PyTorch on Apple Silicon, required by models such as Decider 5. Start Deqio: ```bash uv run deqio serve ``` The first start of a model may download its weights. --- ### Linux — NVIDIA GPU Deqio uses the **CUDA** backend on Linux. 1. Make sure the NVIDIA driver is working: ```bash nvidia-smi ``` 2. Install `uv`: ```bash curl -LsSf https://astral.sh/uv/install.sh | sh ``` 3. Clone and install Deqio: ```bash git clone https://github.com/ILuce/deqio.git cd deqio uv sync ``` 4. Choose a CUDA-compatible model: ```bash uv run deqio models setup ``` 5. Start Deqio: ```bash uv run deqio serve ``` --- ### Windows — NVIDIA GPU Deqio uses the **CUDA** backend on Windows. 1. Make sure the NVIDIA driver is working in PowerShell: ```powershell nvidia-smi ``` 2. Install `uv`: ```powershell powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" ``` 3. Clone and install Deqio: ```powershell git clone https://github.com/ILuce/deqio.git cd deqio uv sync ``` 4. Choose a CUDA-compatible model: ```p