20 tagged on-device-ai, measured the same way as everything else here.
Browse within: Gemma 9ios 9litert 9local-agent 9mobile-agent 9edge-ai 6generative-ai 6
Skill Claude CodeCodex
Reviews a pull request, diff, or branch against Thunderbolt's house rules (no any, type-over-interface, arrow fns, const/early-return, no error-swallowing or defensive code, useReducer at 3+ useState, useEffect discipline, route code-splitting, soft-deletes, integration-agnostic logic) and the 80 architecture…
Skill Claude CodeCodex
MLX Swift LM - Run LLMs and VLMs on Apple Silicon using MLX. Covers local inference, streaming, wired memory coordination, tool calling, LoRA fine-tuning, embeddings, and model porting.
Skill Claude CodeCodex
MLX Swift - High-performance ML framework for Apple Silicon with lazy evaluation, automatic differentiation, and unified memory.
Skill Claude CodeCodex
A contact-management skill for finding, adding, changing, and removing people in an address book.
Skill Claude CodeCodex
Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long…
Skill Claude CodeCodex
Convert a PyTorch or Hugging Face model into a LiteRT model that runs fully on the GPU via the CompiledModel API with verified-correct output, and lay it out as a model recipe. Use when converting a new model, or when a converted model is rejected by the GPU, falls back to CPU, or returns wrong numbers on device.
Skill Claude CodeCodex
Rapidly migrate an Android application from legacy TensorFlow Lite (TFLite) to modern LiteRT CompiledModel API v2.1.6 in Open Source GitHub repositories. Supports True Async Execution (runAsync), Zero-Copy I/O Buffers, NPU JIT compilation, and automated 2-stage verification self-testing.
Skill Claude CodeCodex
An offline knowledge manager based on PARA, a way to organize information into Projects, Areas, Resources, and Archives. It organizes notes, searches them by meaning, and combines related information on the user's device.
sygnalinc/Apple-Frameworks-for-TouchDesigner
Skill Claude CodeCodex
A guide for building TouchDesigner projects with Apple Frameworks custom operators, which are components for tasks such as pose, face, and hand detection, speech transcription, screen capture, and image upscaling.
sygnalinc/Apple-Frameworks-for-TouchDesigner
Skill Claude CodeCodex
A skill for building TouchDesigner native custom operators, called .plugin files, with Apple's on-device frameworks. The listed frameworks include Vision, Core ML, Core Image, Metal, speech, sound, language, screen capture, and reality tools.
Skill Claude CodeCodex
Use web-ai-sdk documentation and package references to build with the Web AI surface.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: