Starred repositories
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
播客音频生成cli ，python服务端 和 web前端，支持单人和多人对话。支持原文智能配音。
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
The batteries-included agent harness.
Active Noise Cancelling Algorithms implementation
[arXiv 2023] Embodied Task Planning with Large Language Models
LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA
👀「大模型」2小时从0训练65M参数的视觉多模态VLM！Train a 65M-parameter VLM from scratch in just 2h!
简单实现VAD+声纹锁+SenseVoice完成类语音实时转录的小项目
Pseudo Streaming SenseVoice with Hotwords
ASR system using transformers neural networks from scratch
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Simple MCP Client for remote MCP Servers 🌐
A working pattern for SSE-based MCP clients and servers
This repository contains demos I made with the Transformers library by HuggingFace.
A Faster LayoutReader Model based on LayoutLMv3, Sort OCR bboxes to reading order.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception
A Unified Toolkit for Deep Learning Based Document Image Analysis
Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.
resp-benchmark is a benchmark tool for testing databases that support the RESP protocol, such as Redis, Valkey, and Tair.
Fully open reproduction of DeepSeek-R1