Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
          nodejs          cmake          ai          metal          json-schema          gpu          vulkan          grammar          cuda          self-hosted          bindings          llama          embedding          cmake-js          prebuilt-binaries          llm          llama-cpp          catai          function-calling          gguf      
    - 
            Updated
            Oct 26, 2025 
- TypeScript