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
A native Capacitor plugin that embeds llama.cpp directly into mobile apps, enabling offline AI inference with chat-first API design. Complete iOS and Android support: text generation, chat, multimodal, TTS, LoRA, embeddings, and more.
Chunk package for the Linux x64 CUDA fallback backend used by node-llama-cpp (1/6)
Use logical overflow properties and values in CSS
High-performance library for inlining CSS into HTML 'style' attributes
High-performance library for inlining CSS into HTML 'style' attributes
Chunk package for the Windows x64 CUDA fallback backend used by node-llama-cpp (1/6)
Use logical overscroll behavior properties and values in CSS
mjml-head-style
Chunk package for the Linux x64 CUDA fallback backend used by node-llama-cpp (5/6)
High-performance library for inlining CSS into HTML 'style' attributes
Inline editor implementation for CKEditor 5.
Inlines img, script and link tags into the same file.
Extract and inline critical css with emotion for server side rendering.
Chunk package for the Linux x64 CUDA fallback backend used by node-llama-cpp (3/6)
Chunk package for the Linux x64 CUDA fallback backend used by node-llama-cpp (2/6)
Adds source mappings and base64 encodes them, so they can be inlined in your generated file.
Chunk package for the Linux x64 CUDA fallback backend used by node-llama-cpp (4/6)
Chunk package for the Windows x64 CUDA fallback backend used by node-llama-cpp (4/6)
Temporarily substitute tokens in the given `string` with placeholders, then put them back after transforming the string.
An inline CSS processor to translate CSS properties to React Native styles.
Turn JSX elements into exploded React objects
Chunk package for the Windows x64 CUDA fallback backend used by node-llama-cpp (3/6)
Chunk package for the Linux x64 CUDA fallback backend used by node-llama-cpp (6/6)