Tinyml Python Packages

abstractintegratedmodule

[~] IntegratedPipeline is a standalone AI Agent Library for Non-LLM memory Augmented Agentic Framework, Specifically designed to provide Agentic capability for any Autonomous Agentic Framework locally and Coordinatively that runs efficiently on small embedded systems to High end embedded systems, While continuously learning and runs efficiently.

tigris-ml

Ahead-of-time compiler that fits ML models on embedded devices with hard memory budgets.

emlearn

Machine Learning inference engine for Microcontrollers and Embedded devices

addernet

Neural "networks" with zero multiplications at inference. AdderNet for embedded systems.

heed-wakeword

Tiny, Apache-2.0 wake-word detection you train yourself and run on-device in Python, the browser, and on mobile.

mantissa-core

Low-precision numerics core for neural networks, in C. Custom float formats (tekin8/tekin32), narrow-store/wide-accumulate, Python bindings. By Tekin Ertekin.

mcufit

Check if an AI model fits on a microcontroller, before you flash it

pulsevad

Ultra-tiny 2.1k streaming voice activity detector (2.1 KB INT8). 200 ms window for microcontrollers, edge devices, and DSPs. ships with ONNX, TorchScript, and standalone C header.

ofa

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

fogml

Source code generators for machine learning models.

signalmap

Unsupervised anomaly detection and predictive maintenance for machine sensor data — vibration, acoustics, motor current — with signed verdicts anyone can verify offline.

miniml-engine

MiniML is a lightweight Machine and Deep Learning framework dedicated to training neural networks in embedded systems, redefining conventional and heavyweight models into different methods that can be exported and executed on low-cost microcontrollers (Arduino, ESP32, STM32).

mlsysim

Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai

pbl-lm

A real engineering language model running fully offline on an $8-class ESP32-S3 — open weights, native C, real-silicon benchmarks.

tinydoc

256M-param document VLM: SigLIP + SmolLM2. LoRA fine-tuning, ONNX export, runs on CPU. Apache 2.0.

deeploy-pulp

DNN Compiler for Heterogeneous SoCs

model2c

tool to convert ML models into low-level inference for embedded platforms

deepc

vendor independent TinyML deep learning library, compiler and inference framework microcomputers and micro-controllers

mcunet

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

emtrees

Machine Learning inference engine for Microcontrollers and Embedded devices

embml

A tool to support using classification models in low-power and microcontroller-based embedded systems.

tinyml-deployer

CLI tool for deploying TensorFlow Lite models to ESP32 and STM32 microcontrollers