Havuz

Two hundred and one agent skills and ten checkers that stop AI coding agents from writing ESP32 firmware that compiles and then kills the bo

把电脑上的 Claude Code、Codex、Gemini、DeepSeek 拉进一个群，组成共享记忆、自己分活的 AI 小团队；一个人调好的 AI，全队都能用。| Bring your local AI CLIs into one group chat as a team w

Whistle speech-to-text running fully on an ESP32-S3: hold a button, say a colour in one of 7 languages, the LED does it. No network.

Edge-cloud vision reference: TFLite gate, MQTT, LLM fallback, temporal memory, calibrated metrology, and a beginner ESP32/serial kit

Desk traffic light for AI coding agents: menu-bar app, terminal dashboard and DIY ESP32-C3 lamp for Claude Code, Codex, opencode and Copilot

Automate your real iPhone from Safari with a $2 ESP32. No Mac, no APP, and no jailbreak. Local conversations, your choice of AI, and communi

A language model trained from scratch and running offline on an ESP32-S3 with a touchscreen chat interface.

A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), stre

Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer acc

让 AI 用自己的手机和号码打真实电话：ESP32 蓝牙桥接，中文控制台，豆包 / OpenAI，Prompt、录音总结与主动重连。

USB desk display showing what your AI coding agents (Claude Code, OpenCode, Codex) are doing — ESP32 firmware, Go helper, 3D-printable enclo

Cornelius, le cadre/miroir intelligent : il vous reconnaît, vous écoute et répond en français. Assistant vocal, reconnaissance faciale en lo

VoiceShell Muse Bridge, ESP32 ile ilk eşleştirmeden sonra Linux sunucusunun Muse ile doğrudan metin alışverişi yapmasını sağlayan deneysel bir köprüdür.

Neden yükseliyor · Bir günlük yaşında 96 yıldız almış; Muse entegrasyonuna yönelik somut test adımları ve başarısız denemeleri de içeren raporlar ilgi çekmiş olabilir. Ancak son 28 gün commit ve farklı yazar verisi ölçülmediğinden geliştirme ivmesi hakkında kanıt yok.

Natural-sounding streaming text-to-speech for the ESP32-S3: 3.3 M params, 3.8 MB of weights, no cloud, no NPU

Meet your agentic companion: a face, a voice and one key for your AI agent.

Oído, ESP32-S3 üzerinde cloud veya NPU olmadan open-vocabulary speech recognition çalıştırmayı hedefleyen C tabanlı bir ASR motorudur.

Neden yükseliyor · Düşük maliyetli bir mikrodenetleyicide open-vocabulary ASR çalıştırma iddiası ve README’de verilen LibriSpeech sonuçları dikkat çekiyor. Repo 1 günlük ve 46 yıldız almış olsa da son 28 gündeki 6 commit’in tek yazardan gelmesi, ilginin henüz bağımsız benimseme veya sürdürülebilir geliştirme kanıtı olmadığını gösteriyor.

Develop and debug FoloToy AI Passport firmware without the device: an ESP32-C3 emulator that runs unmodified ESP-IDF images in the browser (

Clawd, the Claude Code mascot, on an ESP32 touchscreen: reacts to what Claude is doing and shows your plan usage. No OAuth, no cloud, zero t

Optimized ESP32-S3/P4 fully offline speech to text and text to speech system for Micropython and AtomVM, featuring a finetuned STT model for

Groki Bot desktop robot (M5Stack CoreS3): firmware, a voice and MCP gateway for your computer, and a hand-off to Grok Bot agents

A workbench that takes your AI gadget from idea to hardware: simulate, wire, flash and configure, with the AI brain running on your own comp

Service status monitoring

Advanced pentest & BadUSB toolkit for the LILYGO T-Dongle-S3 (ESP32-S3 Device) HID, Deauth, EvilAP, MCP AI and more - Web Flasher Online

面向智能设备的开源 AI 音视频固件. Open-source AI audio and video firmware for smart devices.

559 K パラメータの日本語 TTS を ESP32-S3 で実時間合成。漢字かな交じり文の形態素解析・アクセント推定まで端末内で走る（M5Stack CoreS3 実機で確認）。推論は依存ゼロの C99、ブラウザ demo あり。arXiv:2608.21378 sanoTT

A 14M-parameter LLM keeps a virtual fish tank alive on an $8 ESP32-S3 — distilled from a 26B teacher into 7.56 MB, no network.

Tiny Engineer, AI coding agent’ların çalışma durumlarını Wi-Fi üzerinden aldığı olaylarla hareket, ekran ve ses tepkilerine dönüştüren, ESP32 tabanlı masaüstü robottur.

Neden yükseliyor · AI coding agent’ların yaygınlaşmasıyla görünür çalışma durumu fikri ilgi çekiyor; 37 günde 395 yıldız ve son 28 günde 44 commit ile 5 farklı yazar, hem erken ilgi hem de kayda değer geliştirme faaliyeti gösteriyor.

Run a 28.9M-parameter TinyLM on ESP32-S3 with an RP2040 OLED display node for fully local embedded AI inference.

Deterministic Wasm sandbox + dual-target C runtime for AI-in-the-loop embedded firmware — from ESP32 down to sub-$1 8-bit MCUs

The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your

Rust inference engine for a 28.9M-parameter PLE TinyLM on the ESP32-S3 — 9.4 tok/s, faster than the C implementation it was ported from

ESP32 desk display for live coding-agent usage windows, reset countdowns, and alerts.

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

Cloud MCP gateway that connects a StackChan desk robot to claude.ai — OAuth 2.1 bridge, reflex daemon, pixel avatar toolkit, and the field n

Desk device that mirrors live Claude Code session state onto a Cheap Yellow Display over BLE

Give Claude Code eyes 👁️ — a camera skill so it can SEE real hardware, displays and wiring: verify a rendered panel, check wiring before pow

AI agent session, voice stick, apps, themes, and games on M5Stick

鲜知贴：可复刻的 ESP32 墨水屏食材保鲜提醒器，包含 H5/Node.js/SQLite 服务端、C3/S3 固件、三色/四色屏渲染和 3D 打印外壳，支持公共托管、本地与自托管部署。

令人感动的记忆系统 —— 检索已通关，我们专注记忆的留白：如何回应最有分量的情感性回忆，以及 AI 最终带给人类的价值。

Beautiful real-time web dashboards for ESP32 / ESP8266 in a few lines of C++ — a modern ESP UI & ESPUI alternative. Offline-first AP + capti

AI-powered voice-note device firmware (ESP32-S3): record, transcribe with Whisper, clean up notes with GPT, and auto-sync Markdown to GitHub

Open-source, fully offline wake word / keyword spotting (KWS) inference engine — ONNX/TFLite <130KB, multi-keyword, multilingual. Train a cu

Your AI usage, quota, and balance — as a desk pet. 🐾 A local companion service that normalizes every AI provider into one LAN feed, plus ESP

AI桌面人形机器人 — ESP32-S3全栈运行，不会开口说话，22种情绪+关系成长+6路舵机AI控制，全栈开源(CC BY-NC-SA 4.0)

A ternary, zero-heap tiny language model that runs inside a $2 microcontroller — bit-exact Python <-> C99 <-> Cortex-M3 (QEMU) parity. Apach

Voice assistant for the M5Stack Cardputer ADV. Two API keys, no middleware — Claude in your pocket.

AI-powered meeting recorder on XIAO ESP32-S3 — live transcription, summaries, and AI chat

Device Context Protocol — bridge LLM agents to physical devices. Sub-50-byte frames, 27.6KB flash / 0.6KB RAM measured on ESP32, capability-