AwesomeRepos
Sign in

Tags / Machine learning /

On-device inference

A runtime or compiler that runs trained models on phones, browsers, or edge devices, such as ONNX Runtime or TFLite.

Repositories

13

Net stars gained, last 7 days

+820

Top-level Tag

Machine learning

Net stars gained each day, last 90 days

2026-09-02: +253 net stars. Most from mlc-ai/web-llm, +177.2026-10-23: +455 net stars. Most from midudev/runonweb.ai, +378.2026-10-24: +233 net stars. Most from midudev/runonweb.ai, +177.2026-10-29: +233 net stars. Most from SheepSeb/tinyworldformer, +168.2026-10-30: +209 net stars. Most from SheepSeb/tinyworldformer, +139.

Peak days

  1. 1

    Sep 2, 2026 +253 net stars (median day +62)

  2. 2

    Oct 23, 2026 +455 net stars (median day +62)

  3. 3

    Oct 24, 2026 +233 net stars (median day +62)

  4. 4

    Oct 29, 2026 +233 net stars (median day +62)

  5. 5

    Oct 30, 2026 +209 net stars (median day +62)

A peak day has at least 2 times the net stars of the median day of this chart, and at least 100 more. For each peak day, the list shows the repositories that gained the most net stars that day. It also shows their GitHub releases of that day or the day before (UTC), and their creation date when it was 14 days or less before. These events occur near the same day. They do not show why the stars came.

Largest

Most stars in total now.

  1. google-ai-edge/mediapipe38K

    readme: MediaPipe contains everything that you need to customize and deploy to mobile (Android, iOS), web, desktop, edge devices, and IoT, effortlessly.

  2. Tencent/ncnn24K

    readme: ncnn is a high-performance neural network inference framework optimized for mobile, embedded, and desktop deployment.

  3. mlc-ai/mlc-llm23K

    readme: MLC LLM is a machine learning compiler and high-performance deployment engine for large language models.

  4. microsoft/onnxruntime22K

    readme: ONNX Runtime is a cross-platform inference and training machine-learning accelerator

  5. mlc-ai/web-llm19K

    readme: WebLLM is a high-performance in-browser LLM inference engine that brings language model inference directly onto web browsers with hardware acceleration.

  6. tensorflow/tfjs19K

    readme: Use TensorFlow.js model converters to run pre-existing TensorFlow models right in the browser.

  7. alibaba/MNN16K

    description: MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

  8. NVIDIA/TensorRT13K

    description: NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs.

  9. openvinotoolkit/openvino11K

    readme: Reduce resource demands and efficiently deploy on a range of platforms from edge to cloud.

  10. midudev/runonweb.ai762

    readme: Free, open-source AI modules that run in the browser.

Newest Admissions

Entered the index by the rising rule, newest first.

  1. SheepSeb/tinyworldformer350

    readme: I wanted to see if a looped world model could be small enough to run on a microcontroller.

  2. opencoredev/bg0488

    readme: It uses WebGPU when available, falls back to WebAssembly, and produces a transparent PNG without uploading the source image.

  3. midudev/runonweb.ai762

    readme: Free, open-source AI modules that run in the browser.

  4. Fruank4/laya-ort381

    readme: This repository runs that decision on ONNX Runtime's CPU, for Intel and AMD machines.

All 13 in the Repository Index

How a repository gets this Tag

An agent reads the description, the GitHub topics, and the start of the README of each repository. It chooses Tags only from the Tag list in the AwesomeRepos source code. For each Tag, it quotes the text. A code check keeps the Tag only when the quote is in that text. The quote under each repository is that evidence. A Tag does not rank repositories. It does not say that one repository can replace another. To report a wrong Tag, use "Report a problem with this page" on the page of the repository. All numbers on this page count only visible repositories.