Stars
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Spec-driven development (SDD) for AI coding assistants.
MCP server to provide Figma layout information to AI coding agents like Cursor
Espressif IoT Development Framework. Official development framework for Espressif SoCs.
Multilingual Voice Understanding Model
一个基于小智、xiaozhi-server的Android、IOS语音对话应用,支持实时语音交互和文字对话。现在是flutter版本，打通IOS、Android端。请同志们动动小手，点点小星星，予以鼓励。
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断
Embedded graphics library to create beautiful UIs for any MCU, MPU and display type.
A Python-based Xiaozhi AI for users who want the full Xiaozhi experience without owning specialized hardware.
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.
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
Wechat Chat History Exporter 微信聊天记录导出备份程序
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…
Download market data from Yahoo! Finance's API
🔥 2D and 3D Face alignment library build using pytorch
Run go programs as a service on major platforms.
Simple, reliable, and efficient distributed task queue in Go
The Go language implementation of gRPC. HTTP/2 based RPC
Go support for Google's protocol buffers
real time face swap and one-click video deepfake with only a single image