A 45M-parameter LLM: needle 2 running fully offline on an ESP32-S3, turning plain-English requests into guaranteed-valid JSON tool calls.

Website to Home Environment Simulator Targeting Inhabitant Activities (HESTIA)

14MB foundation model for tiny devices; phones, wearables, smart home, and robots.

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.

ESP-Claw, a "Chat Coding" AI agent framework for IoT devices

Repeatable agents-plus-code workflows, packaged as one skill, stamped into any repo. Deterministic Python owns the graph; coding agents are bounded nodes inside it.

Where Human Intelligence and Artificial Intelligence Collaborate

A skill to stop your coding agent from burying the answer. ADHD-friendly output.

Event-sourced graph runtime for durable and stateful agents

The strictest and most opinionated python linter ever!

Git-backed multi-agent orchestration protocol for smart homes. Lease-gated actuation, conflict resolution, and crash-safe recovery on commodity edge hardware. CAIS 2026.

Native iOS conversational house consciousness app

Multi-agent intelligent control framework designed to optimize household energy consumption while maintaining safety and user comfort

23 Components of the Claude Code Architecture

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Voice assistant for Android tablets with Home Assistant integration

Collection of all my publicly accessible skills

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

Self-hosted, OpenAI-compatible speech server: faster-whisper STT and Piper/Kokoro TTS. A local voice backend for Open WebUI, CLIs, and custom agents.

Add a [DeepWiki] button to quickly access DeepWiki from GitHub repositories

The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. Industrial protocols (OPC-UA, Modbus) on the roadmap.

This repository contains the implementation of a fully local, offline conversational edge AI system

This repository provides a highly modular, end-to-end benchmarking framework designed to evaluate and compare locally hosted AI models for Conversational Voice Assistants.

Realtime Voice AI Toys with 100+ Models on Arduino ESP32 with Secure Websockets and Edge Functions for AI Companions, and Devices

Ultra-Low-Cost Portable AI Voice Assistant MVP (ESP32-S3 & DeepSeek)

本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.