Repo đang lênCập nhật hằng ngày từ GitHub

This is an LLM-based code reader.

中文医疗对话模型扁鹊(BianQue)

A pytorch library for graph and hypergraph computation.

LM Studio Python SDK

Expose Gemini CLI endpoints as OpenAI API with Cloudflare Workers

tfts: Time Series Deep Learning Models in TensorFlow

A backend for web, mobile, AI and IoT apps. Built on MongoDB

Computer Vision in Python

A fork of Anthropic Computer Use that you can run on Mac computers to give Claude and other AI models autonomous access to your computer.

AI 自动回复工具，支持灵活配置多个平台的监控和回答。目前已支持知识星球自动回复、OpenAI（ChatGPT）自动回答

Train and Deploy an ML REST API to predict crypto prices, in 10 steps

Collection of audio-focused loss functions in PyTorch

Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening

Awesome work on object 6 DoF pose estimation

Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.

Code for a series of work in LiDAR perception, including SST (CVPR 22), FSD (NeurIPS 22), FSD++ (TPAMI 23), FSDv2, and CTRL (ICCV 23, oral).

[CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

🎯🗯 Dataset generation for AI chatbots, NLP tasks, named entity recognition or text classification models using a simple DSL!

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

A unified multimodal language model based on discrete sequence modeling

Pre-compiled Python whl for Flash-attention, SageAttention, NATTEN, xFormer etc

All-In-One Music Structure Analyzer

Portuguese pre-trained BERT models

Implementation of Dreamer v3 in pytorch.

An local, offline (after initial setup), portable OCR software that can process images and PDF files, using DeepSeek-OCR-2 AI (running directly on your machine).

A copy-paste system prompt that has your coding agent (Claude Code, Codex, Cursor) build a self-improving agent system for any computer work.

[CMU] A Versatile and Modular Framework Designed for Autonomous Unmanned Aerial Vehicles [UAVs] (C++/ROS/PX4)

GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training

Generating faces with deconvolution networks

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

Turn messy, real-world HTML into clean Markdown, from every major language.

在线考试系统

JevChat-Windows：聊天窗口旁挂的回复辅助。窗口截图 + 本地离线 OCR 读对方消息 → Jev 判断意图 → 3 条候选一键填入，发送永远手动

Code2Prompt is a powerful command-line tool that simplifies the process of providing context to Large Language Models (LLMs) by generating a comprehensive Markdown file containing the content of your codebase. ⭐ If you find Code2Prompt useful, consider giving us a star on GitHub! It helps us reach more developers and improve the tool. ⭐

🤖 A PyTorch library of curated Transformer models and their composable components

Train and serve LLMs at extreme speed and massive throughput.

SOMA: Unifying Parametric Human Body Models

Simple PyTorch implementations of U-Net/FullyConvNet (FCN) for image segmentation

sbi is a Python package for simulation-based inference, designed to meet the needs of both researchers and practitioners. Whether you need fine-grained control or an easy-to-use interface, sbi has you covered.

『ゼロから作る Deep Learning ❸』(O'Reilly Japan, 2020)

ChatGPT and Bing AI prompt curation

LSP server leveraging LLMs for code completion (and more?)

Replit容器部署xray代理，支持argo固定隧道与临时隧道，自定义伪装网页，一键五协议共存，支持搭建vless、vmess、trojan、shadowsocks、socks5

PyTorch从入门到精通

A comprehensive open-source reference for backend engineering HTTP, concurrency, gRPC, distributed systems, observability, and cloud-native deployment. Built from first principles.

The Implementation of FastSpeech based on pytorch.

Native iPhone and iPad console for herdr: watch and drive coding agents on your machines over SSH, in Herdr TUI or the Herdr desktop app (herdr-core), with a real libghostty terminal, native Chat, QR pairing, and push notifications when an agent needs you

🦍 Memorilla: Latent Semantic Memory for LLMs

Markdown knowledge base with bidirectional [[link]]s built on top of VSCode

Virtually controlling computer using hand-gestures and voice commands. Using MediaPipe, OpenCV Python.