InkTime 是一个可自托管的墨水屏电子相框。它用AI分析你的照片库，按值得回忆度打分，并按“历史上的今天”自动生成每日最具回忆价值的照片，让沉睡的记忆重新被看见。

Bili-Insights 是一个用于抓取、统计并可视化 B 站 UP 主数据的轻量级工具。 特点是：本地部署、每日快照、可视化看板、支持视频数据与账号数据分析。

Xiaomi MiMo-VL-Miloco

Xiaomi Miloco

LVGL ported to ESP32 including various display and touchpad drivers

LVGL is a free, full-featured embedded UI library for devices from small MCUs to 3D-capable MPUs, enhanced by LVGL Pro, a professional editor and tooling.

AI 视频笔记生成工具 让 AI 为你的视频做笔记

A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval

Lets make video diffusion practical!

A collection of MCP servers.

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

AI for Science 论文解读合集（持续更新ing），论文/数据集/教程下载：hyper.ai

🏠 将小爱音箱接入 ChatGPT 和豆包，改造成你的专属语音助手。

ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Faster Whisper transcription with CTranslate2

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without …

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

esp32 based device, mainly used for voice chat with large language models

Python3编写的各种大小程序，包含从零学Python系列、12306抢票、省市区地址库以及系列网站爬虫等学习源码

Play ChatGPT and other LLM with Xiaomi AI Speaker

使用PyQt5封装了小米音箱连接ChatGPT的客户端

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

Linux kernel source tree

An MPEG2 video decoder, written in Verilog and implemented in an FPGA chip.