Updated today
by google-ai-edge
litert-samples
LiteRT and LiteRT-LM sample apps, model recipes, agent skills and utilities.
463 GitHub stars (463)
+16 in 16 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 |
- 7 skills (7 skills found in its SKILL.md files)
- 122 forks (122 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/SKILL.md on GitHub (opens in a new tab) -
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/SKILL.md on GitHub (opens in a new tab) -
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/SKILL.md on GitHub (opens in a new tab) -
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/SKILL.md on GitHub (opens in a new tab) -
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. Covers buffer reuse, NPU JIT compilation, a reference implementation, and a two-stage verification gate (compile check, then an on-device parity test against a golden output).
skills/litert-compiled-model-migration/SKILL.md on GitHub (opens in a new tab) -
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/SKILL.md on GitHub (opens in a new tab) -
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/SKILL.md on GitHub (opens in a new tab)
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…
-
superpowersby obra An agentic skills framework & software development methodology that works.
-
skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
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.