all publishers

google-ai-edge

@google-ai-edge source repo

29 published skills

  1. ▌
    Create Litert Lm Android Demo App · google-ai-edge bundle
    Guides the agent to orchestrate and implement a standalone LiteRT-LM Android demo app with backend selection and multi-modality support using Bazel 9. Use when asked to create a demo app for LiteRT-LM on Android. Don't use for general Android app development without LiteRT-LM, or for building the core library alone without an app.
    25.3k repo stars
  2. ▌
    Litert Cc Sdk Prebuilt Onboarding · google-ai-edge bundle
    Onboards, builds, and deploys open-source (OSS) C++ LiteRT CompiledModel applications using the prebuilt litert_cc_sdk headers and libLiteRt (.so/.dll/.dylib) archive via CMake dynamic linking across Linux, Android, Windows (x86_64 and arm64), and Qualcomm IoT on CPU, GPU (OpenCL/WebGPU), and Qualcomm NPU (AOT and JIT). Use when integrating LiteRT prebuilt zip archives into an external CMake project without building LiteRT from source, placing GPU accelerator or Qualcomm QNN NPU dispatch/plugin libraries, running apply_plugin_main for offline AOT compilation, or troubleshooting QNN version and FastRPC Skel errors.
    25.3k repo stars
  3. ▌
    Auto Quant 2 · google-ai-edge bundle
    Systematically explore quantization configurations for a TFLite model using the LiteRT Quantizer API, finding the optimal recipe that balances file size and accuracy. Use this skill whenever the user wants to quantize a model, optimize a recipe, explore quantization tradeoffs, minimize size bounds, or perform selective quantization using LiteRT Quantizer framework. Applies to any model scale and modality: CNNs, segmentation nets, classifiers, embedding models, audio models, and LLMs.
    25.3k repo stars
  4. ▌
    Mood Tracker 2 · google-ai-edge bundle
    A simple mood tracking skill that stores your daily mood and comments. Use this when the user wants to log their mood, track how they feel, or see their mood history.
    25.3k repo stars
  5. ▌
    Text Spinner 2 · google-ai-edge bundle
    Spin the given text on my head.
    25.3k repo stars
  6. ▌
    Mood Music 2 · google-ai-edge bundle
    A skill to suggest or play music based on the user's mood, including analyzing images or audio, by querying available genres and generating music via the Loudly API.
    25.3k repo stars
  7. ▌
    Virtual Piano 2 · google-ai-edge bundle
    Show a virtual piano to play music
    25.3k repo stars
  8. ▌
    Restaurant Roulette 2 · google-ai-edge bundle
    Show a roulette wheel to allow user to randomly select a restaurant based on location and cuisine.
    25.3k repo stars
  9. ▌
    Mood Music · google-ai-edge bundle
    A skill to suggest or play music based on the user's mood, including analyzing images or audio, by querying available genres and generating music via the Loudly API.
    25.3k repo stars
  10. ▌
    Virtual Piano · google-ai-edge bundle
    Show a virtual piano to play music
    25.3k repo stars
  11. ▌
    Restaurant Roulette · google-ai-edge bundle
    Show a roulette wheel to allow user to randomly select a restaurant based on location and cuisine.
    25.3k repo stars
  12. ▌
    Mood Tracker · google-ai-edge bundle
    A simple mood tracking skill that stores your daily mood and comments. Use this when the user wants to log their mood, track how they feel, or see their mood history.
    25.3k repo stars
  13. ▌
    Text Spinner · google-ai-edge bundle
    Spin the given text on my head.
    25.3k repo stars
  14. ▌
    Auto Quant · google-ai-edge bundle
    Systematically explore quantization configurations for a TFLite model using the AI Edge Quantizer API, finding the optimal recipe that balances file size and accuracy. Use this skill whenever the user wants to quantize a model, optimize a recipe, explore quantization tradeoffs, minimize size bounds, or perform selective quantization using AI Edge Quantizer (or AEQ) framework. Applies to any model scale and modality: CNNs, segmentation nets, classifiers, embedding models, audio models, and LLMs.
    25.3k repo stars
  15. ▌
    Litert CLI · google-ai-edge
    LiteRT CLI tool to download, convert, quantize, run, benchmark, and visualize LiteRT models.
    25.3k repo stars
  16. ▌
    Converting Pytorch To Litert · google-ai-edge bundle
    Converts PyTorch models (e.g. ResNet, timm, HuggingFace transformers) directly to LiteRT (.tflite) flatbuffer format. Use when converting PyTorch models to TFLite, setting up export environments, or troubleshooting torch-to-litert conversion bugs. Don't use for ONNX exports or converting existing TensorFlow models.
    25.3k repo stars
  17. ▌
    Litert Model Equivalence Test · google-ai-edge bundle
    Validates equivalence between LiteRT models (litert_lm) and PyTorch models (transformers). Use when you need to verify that an exported LiteRT model produces the same outputs as the original Hugging Face model. Supports multi-turn conversations and custom prompts.
    25.3k repo stars
  18. ▌
    Litert Quantization Calib · google-ai-edge
    Assists the user to calibrate, merge, and statically quantize litert LLM models (such as Gemma 3) in standard open-source (OSS) environments. Use when the user wants to run LLM calibration, merge task JSON results, align KV cache parameters across models, protect sensitive layers in Float32, or run quantized inference testing. Don't use for JAX/PyTorch custom quantization configurations or non-litert models.
    25.3k repo stars
  19. ▌
    Calculate Hash · google-ai-edge bundle
    Calculate the hash of a given text.
    25.3k repo stars
  20. ▌
    Learn Something New · google-ai-edge bundle
    A daily learning companion that teaches users a new concept, generates a beautiful image card, and schedules recurring daily learning notifications.
    25.3k repo stars
  21. ▌
    Read Calendar Events · google-ai-edge
    Read OS calendar events for a specific date.
    25.3k repo stars
  22. ▌
    Create Calendar Event · google-ai-edge
    Create a calendar event.
    25.3k repo stars
  23. ▌
    Schedule Notification · google-ai-edge
    Schedule a notification for a specific date or repeating daily.
    25.3k repo stars
  24. ▌
    Gpu Clean Conversion · google-ai-edge
    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.
    25.3k repo stars
  25. ▌
    On Device Verification · google-ai-edge
    Prove a converted or quantized LiteRT model on the actual device via the CompiledModel API - confirm GPU residency, compare device output against the source model, and diagnose device-only failures such as silent CPU fallback, whole-graph compile ceilings, and fp16 range breaks. Use after conversion or quantization, when device output is wrong or NaN, when a clean graph fails to compile only on device, or when GPU and CPU outputs are suspiciously identical.
    25.3k repo stars
  26. ▌
    Accuracy Safe Quantization · google-ai-edge
    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 generations, or when deciding between dynamic-range, weight-only, and blockwise variants.
    25.3k repo stars
  27. ▌
    Litert Conversion Workflow · google-ai-edge bundle
    Convert a Hugging Face LLM or vision-language model checkpoint into a .litertlm bundle that runs on the LiteRT-LM runtime with verified quality - classify the architecture against known runtime walls, pick the recipe family (dense, reasoning, hybrid SSM, VLM), export, quantize, gate the result against the source model, and publish. Use when converting a new LLM or VLM to LiteRT-LM, when a converted bundle crashes on the first message or dies at engine creation, when a quantized model answers worse than its source, or when deciding whether a model is convertible at all.
    25.3k repo stars
  28. ▌
    Compiled Model App Scaffolding · google-ai-edge
    Build a new Android app (Kotlin, Compose) around a verified LiteRT model using the CompiledModel API - the app architecture, the inference-layer lifecycle rules, model delivery, and the UI traps that masquerade as model bugs. Use when turning a converted and device-verified model into a demo or product app, when an app's inference layer leaks memory or blocks the UI, or when a model that verified clean looks wrong inside an app.
    25.3k repo stars
  29. ▌
    Litert Compiled Model Migration · google-ai-edge bundle
    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.
    25.3k repo stars