Repo đang lênCập nhật hằng ngày từ GitHub

TinyChatEngine: On-Device LLM Inference Library

A curated list of awesome resources related to capsule networks

NequIP is a code for building E(3)-equivariant interatomic potentials

Agent communication SDK. The open-source agent communication layer for AI agents — email, WhatsApp, Slack, Discord, Telegram, SMS. Python & TypeScript.

An open-source educational chat model from ICALK, East China Normal University. 开源中英教育对话大模型。(通用基座模型，GPU部署，数据清理) 致敬: LLaMA, MOSS, BELLE, Ziya, vLLM

Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.

Official implementation of Diffusion Autoencoders

ICCV 2023-2025 Papers: Discover cutting-edge research from ICCV 2023-25, the leading computer vision conference. Stay updated on the latest in computer vision and deep learning, with code included. ⭐ support visual intelligence development!

Running Llama 2 and other Open-Source LLMs on CPU Inference Locally for Document Q&A

DeepSeek Harness (dsh) 从 0 到 1 深度手册：安装/插件开发/性能调优/实测案例/同模型多 Agent 实测对比（中文 + 英文 PDF）

Machine Learning Q and AI book

:art: Pytorch YOLO v5 训练自己的数据集超详细教程！！！ :art: (提供PDF训练教程下载）

An intelligent reverse engineering and AI-assisted analysis tool for HarmonyOS NEXT (HAP/APP/ABC), Android (APK/AAB), iOS (IPA), and native PE/ELF/Mach-O binaries.

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory

Transformer models from BERT to GPT-4, environments from Hugging Face to OpenAI. Fine-tuning, training, and prompt engineering examples. A bonus section with ChatGPT, GPT-3.5-turbo, GPT-4, and DALL-E including jump starting GPT-4, speech-to-text, text-to-speech, text to image generation with DALL-E, Google Cloud AI,HuggingGPT, and more

Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?"

🐉 Dante Cloud 是支持阻塞式与响应式服务并行的微服务云原生基座和面向AI Agent开发的智能基座，基于领域驱动模型（DDD）设计，以高质量代码与低安全漏洞为核心，高度模块化、组件化，覆盖IoT设备认证、国家等保三级、接口国密数字信封加密等多层次安全体系，并提供多租户解决方案。独创“一套代码实现微服务和单体架构灵活切换”，赋能企业级智能应用构建。🔝🔝点个star 持续关注更新！

OpenEverest is an open-source platform for automated database, storage and LLMs provisioning and management. It supports multiple technologies and can be hosted on any Kubernetes infrastructure, in the cloud or on-premises.

Open source project for data preparation for GenAI applications

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.

The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.

Processed / Cleaned Data for Paper Copilot

List of awesome hosting sorted by minimal plan price

PINNs-Torch, Physics-informed Neural Networks (PINNs) implemented in PyTorch.

ChatGPT CLI is a powerful, multi-provider command-line interface for working with modern LLMs. It supports OpenAI, Azure, Perplexity, LLaMA, and more, with features like streaming, interactive chat, prompt files, image/audio I/O, MCP tool calls, and an experimental agent mode for safe, multi-step automation.

[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free

PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic coordination, and parallel autonomous operations.

A CLI-based, flat-file issue tracker for humans and robots. 🤖

Ally-Health is an intelligent healthcare assistant that harnesses advanced AI technology and medical expertise to transform personal health management. Through natural language interaction, it helps users record symptoms, manage medications, organize medical records, and access multidisciplinary health insights—making healthcare more intelligent, p

Label images and video for Computer Vision applications

online 3d openpose editor for stable diffusion and controlnet

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

Pytorch implementation of MixNMatch

AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.

整理目前开源的最优表格识别模型，完善前后处理，模型转换为ONNX | Organize the currently open-source optimal table recognition models, improve pre-processing and post-processing, and convert the models to ONNX.

Official implementation of Half-Quadratic Quantization (HQQ)

China's 1st enterprise multi-agent IT ops platform. LLM-powered auto-remediation for Zabbix/Prometheus. Docker deploy.

The IM for agents. Shared Agent Context & Memory, supervised execution, and cross-agent audit across AI providers.

One-command installer for a self-hosted AI stack on your own server: n8n, Ollama, Open WebUI, OpenClaw, Dify, Flowise, Supabase, ComfyUI, Qdrant & 30+ tools. Docker Compose, automatic HTTPS via Caddy, built-in monitoring. Free Zapier/Make alternative.

jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.

PyTorch implementation of normalizing flow models

A collection of implementations of deep domain adaptation algorithms

A multi-platform desktop application to evaluate and compare LLM models, written in Rust and React.

Transparent Python RAG reference with FAISS + BM25 hybrid retrieval, reranking, Gradio UI, and FastAPI.

RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.

GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)

go version of tiktoken

Code for 3D object detection for autonomous driving