<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Edge-Ai on Noureddine RAMDI</title><link>https://ramdi.fr/tags/edge-ai/</link><description>Recent content in Edge-Ai on Noureddine RAMDI</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 23 May 2026 20:41:27 +0000</lastBuildDate><atom:link href="https://ramdi.fr/tags/edge-ai/index.xml" rel="self" type="application/rss+xml"/><item><title>esp-claw: running a full AI agent loop on ESP32 edge devices</title><link>https://ramdi.fr/github-stars/esp-claw-running-a-full-ai-agent-loop-on-esp32-edge-devices/</link><pubDate>Tue, 05 May 2026 13:37:39 +0000</pubDate><guid>https://ramdi.fr/github-stars/esp-claw-running-a-full-ai-agent-loop-on-esp32-edge-devices/</guid><description>esp-claw runs a complete AI agent loop locally on ESP32 chips, integrating Lua scripting, MCP protocol, and LLM APIs for on-device decision making with millisecond response times.</description></item><item><title>LiteRT-LM: Google's C++ library for efficient edge language model inference</title><link>https://ramdi.fr/github-stars/litert-lm-google-s-c-library-for-efficient-edge-language-model-inference/</link><pubDate>Mon, 04 May 2026 10:23:02 +0000</pubDate><guid>https://ramdi.fr/github-stars/litert-lm-google-s-c-library-for-efficient-edge-language-model-inference/</guid><description>LiteRT-LM is a Google AI Edge C++ library for performant language model inference on edge devices with multi-language API support and easy CLI usage.</description></item><item><title>MicroGPT-C: Coordinating tiny GPT-2 models in C for edge logical reasoning</title><link>https://ramdi.fr/github-stars/microgpt-c-coordinating-tiny-gpt-2-models-in-c-for-edge-logical-reasoning/</link><pubDate>Mon, 04 May 2026 10:23:02 +0000</pubDate><guid>https://ramdi.fr/github-stars/microgpt-c-coordinating-tiny-gpt-2-models-in-c-for-edge-logical-reasoning/</guid><description>MicroGPT-C uses a deterministic C scaffold to coordinate tiny GPT-2 models, achieving 90%+ accuracy on logic games with 8x memory compression and infinite sequence lengths.</description></item></channel></rss>