A curated list of awesome embedded programming.
Embedded and mobile deep learning research resources
Embedded agents your customers use to automate work, build views, and connect their tools.
Full face stack that runs entirely in the browser. Detection, 576-point 3D mesh, recognition, anti-spoof, smile — all WebAssembly, zero server. Apache 2.0.
benchmark for embededded-ai deep learning inference engines, such as NCNN / TNN / MNN / TensorFlow Lite etc.
Noodle provides primitive modular functions for convolution layer, dense layer, pooling and activations. It allows streaming the intermediate activations, weights, and biases from/to SD/FFat/SD_MMC filesystems to overcome RAM limitations.
Read chapters directly from this repo - do not use GitHub Pages link.
Legend of Elya — N64 game with a real 6.36M-parameter ternary transformer on the VR4300 MIPS III CPU. Zelda-style dungeon, AI NPCs, byte-level inference at 1.23 tok/s scalar / 2.19 tok/s on the RSP overlay (measured under ares, never on silicon). Built with libdragon.
414 KB WASM runtime for Needle a 14M-parameter tool-calling transformer. Runs in browser, Cloudflare Workers, and Node.js. No backend required.
POC visual search with smart glasses and Qdrant Edge.
World's First NMS-Free YOLOv26n on ESP32-P4. Features end-to-end Int8 QAT and custom C++ optimizations achieving 30% faster inference than the official ESP-DL YOLOv11n (1.7s vs 2.4s).
Run a 28.9M-parameter TinyLM on ESP32-S3 with an RP2040 OLED display node for fully local embedded AI inference.
This guide walks you through setting up a lightweight Large Language Model (LLM) on a Raspberry Pi Zero 2 W. We’ll use Raspberry Pi OS (Legacy, 64-bit) Lite, optimize the Pi for better performance, and install the Ollama application to run the model.
RPI (Resonant Permutation Inference) — Zero-multiply text generation. 18K tok/s. 868 KB models. Standalone or as speculative draft engine for LLMs. Runs on N64, POWER8, x86, ARM.
Open-source Hardware AI agent. Single Rust binary for cameras, sensors, robots, and IoT fleets — orchestrated by AI agents with memory and real-time telemetry. Runs on Jetson, Raspberry Pi, any Linux.
AcousticsLab is a cross-platform framework for sound and vibration analysis.
Culturally-compliant video storage. Embeds searchable text chunks into pixelated media for lightning-fast semantic search. Zero-database, maximum compliance.
Ultra-lightweight C++ inference engine for BitMamba-2 (1.58-bit SSM). Runs 1B models on consumer CPUs at 50+ tok/s using <700MB RAM. No heavy dependencies.
Speech Recognition using STM32 and Machine Learning
Auditable offline edge intelligence for low-cost edge devices, with benchmark evidence and public board proof on ESP32-C3.
To associate your repository with the embedded-ai topic, visit your repo's landing page and select "manage topics."