esp-dl
Deploy and optimize neural networks on ESP32 chips with AI agents
All Skills in This Repository (4)
Pure Emerald Level Indicators
espressifespdl-operator
Implement, test and optimize neural network operators for the ESP-DL framework.
espressifesp32p4-simd
Converts scalar code into ESP32-P4 PIE SIMD assembly for neural network operators.
espressifESP32-S3 PIE SIMD Optimization
Converts scalar C loops into ESP32-S3 PIE SIMD assembly using EE.* instructions.
espressifespdl-quantize
Automates iterative esp-ppq quantization tuning to recover accuracy on ESP-DL models.
Frequently Asked Questions
FAQPage SchemaHow to install ESP-DL skills?▼
Run `npx skills add espressif/esp-dl --all -g -y` in your terminal to install all agent skills in this suite globally.
What does ESP-DL do?▼
ESP-DL is a lightweight neural network inference framework for ESP32 chips, with APIs to load, quantize, and run AI models on-device.
How to improve quantized model accuracy on ESP32?▼
The espdl-quantize skill automatically searches esp-ppq quantization settings in iterations to recover accuracy lost during quantization.
Can AI agents write SIMD assembly for ESP32?▼
Yes. The esp32s3-pie-simd and esp32p4-pie-simd skills teach agents to convert scalar C loops into optimized PIE SIMD instructions.
Do I need embedded experience to use these skills?▼
No. Your AI agent follows the skill instructions to handle operator implementation, testing, and optimization from plain-English requests.
Related Repositories in Software Engineering
View All in Software Engineering→
openclawopenclaw
Run a personal AI assistant across your devices and chat apps
obrasuperpowers
Gives coding agents a disciplined workflow from idea to merged code
facebookreact
AI agent skills for building, testing, and porting React core