Updated today
by google-ai-edge
litert-samples
LiteRT and LiteRT-LM sample apps, model recipes, agent skills and utilities.
486 GitHub stars (486)
+28 in 30 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | +1 |
| Oct 3 | +3 |
| Oct 4 | +6 |
| Oct 5 | +1 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | +1 |
| Oct 10 | 0 |
| Oct 11 | +3 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | −1 |
| Oct 16 | +2 |
| Oct 17 | +2 |
| Oct 18 | 0 |
| Oct 19 | 0 |
| Oct 20 | +1 |
| Oct 21 | +1 |
| Oct 22 | 0 |
| Oct 23 | +3 |
| Oct 24 | +1 |
| Oct 25 | +2 |
| Oct 26 | 0 |
| Oct 27 | 0 |
| Oct 28 | 0 |
| Oct 29 | +2 |
| Oct 30 | +2 |
| Oct 31 | +4 |
| Nov 1 | 0 |
| Nov 2 | +2 |
| Nov 3 | 0 |
| Nov 4 | +3 |
| Nov 5 | 0 |
- 12 skills (12 skills found in its SKILL.md files)
- 132 forks (132 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add google-ai-edge/litert-samples
Asks which skills and agents to install. Just one: npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization — add -g for every project.
Claude Code
git clone https://github.com/google-ai-edge/litert-samplescp -r "litert-samples/skills/accuracy-safe-quantization" ~/.claude/skills/
Copies the accuracy-safe-quantization skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add google-ai-edge/litert-samples
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
accuracy-safe-quantization
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.
skills/accuracy-safe-quantization/ on GitHub (opens in a new tab)SKILL.md -
benchmark-on-ddp
Measure a LiteRT .tflite model with `benchmark_model` on Developer Device Platform (DDP) lab phones through `litert benchmark --ddp`, or on the Mac you run it from, and turn the session into rows of the performance leaderboard under benchmark/leaderboard - one matrix entry per model, one session per accelerator, collect results.pb and runtime_info.pb, rebuild board.json, check the page, commit th…
skills/benchmark-on-ddp/ on GitHub (opens in a new tab)SKILL.md -
compiled-model-app-scaffolding
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…
skills/compiled-model-app-scaffolding/ on GitHub (opens in a new tab)SKILL.md -
gpu-clean-conversion
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.
skills/gpu-clean-conversion/ on GitHub (opens in a new tab)SKILL.md -
litert-compiled-model-migration
Rapidly migrate an Android application from legacy TensorFlow Lite (TFLite) to the modern LiteRT CompiledModel API (2.x) in Open Source GitHub repositories, keeping the TensorFlow Lite Support Library as LiteRT Support (litert-support 2.3.0). Covers buffer reuse, NPU JIT compilation, a reference implementation, and a two-stage verification gate (compile check, then an on-device parity test agains…
skills/litert-compiled-model-migration/ on GitHub (opens in a new tab)SKILL.md -
litert-conversion-workflow
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 convert…
skills/litert-conversion-workflow/ on GitHub (opens in a new tab)SKILL.md -
litert-google-tensor
Compiles LiteRT (.tflite) models ahead-of-time for Google Tensor TPUs (Tensor G5 on Pixel 10, Tensor G6 on Pixel 11) locally on Linux x86_64 or remotely via Google Colab (--colab on macOS, Windows, or ARM hosts), benchmarks them on a USB-attached Pixel with LiteRT's benchmark_model (NPU latency, peak memory, TPU tile time, TPU energy, optional CPU baseline), and packages compiled models for an An…
skills/litert-google-tensor/ on GitHub (opens in a new tab)SKILL.md -
litert-lm
Creates an Android app that runs an open text LLM on the device, on the CPU or the GPU, with the LiteRT-LM Kotlin API. LiteRT-LM is the recommended replacement for the MediaPipe LLM Inference API (com.google.mediapipe:tasks-genai), which is in maintenance-only mode. Use this skill to build a new chat, summarization or extraction app with a .litertlm model from Hugging Face litert-community (Gemma…
skills/litert-lm/ on GitHub (opens in a new tab)SKILL.md -
litert-runtime
Configures and implements LiteRT (.tflite) on-device inference on Android in Kotlin using the CompiledModel API on CPU and GPU. Use this skill for any Android LiteRT or .tflite task, including Gradle setup, image classification or vision/audio/embedding helpers, TensorBuffer reuse, Bitmap preprocessing, AndroidViewModel GPU-to-CPU fallback with warm-up on a single-thread dispatcher, migrating fro…
skills/litert-runtime/ on GitHub (opens in a new tab)SKILL.md -
on-device-verification
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 d…
skills/on-device-verification/ on GitHub (opens in a new tab)SKILL.md -
current-time
Get the current local time, date and day of the week.
samples/litert/ on GitHub (opens in a new tab)flutter/ assets/ skills/ current-time/ SKILL.md -
device-info
Say which models, backends and accelerators this app is running and how much memory the device has.
samples/litert/ on GitHub (opens in a new tab)flutter/ assets/ skills/ device-info/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
uiby shadcn-ui Composable, accessible components with thoughtful defaults. Build your own component library with code you can customize, extend, and make…
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory.
-
superpowersby obra An agentic skills framework & software development methodology that works.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.