Repo AI đang lênCập nhật hằng ngày từ GitHub

Java interface to OpenCV, FFmpeg, and more

Use your locally running AI models to assist you in your web browsing

A collection of libraries to optimise AI model performances

BoxMOT: Pluggable Python and C++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes

Giving Kubernetes Superpowers to everyone

Trax — Deep Learning with Clear Code and Speed

The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

Open-source Grok Bot alternative. Choose your own model and sandbox.

Stable Diffusion built-in to Blender

Pytorch implementation of convolutional neural network visualization techniques

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama). BYOK, local-first, MIT.

BertViz: Visualize Attention in Transformer Models

Curated list of awesome tools, demos, docs for ChatGPT and GPT-3

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

Contains Solutions and Notes for the Machine Learning Specialization By Stanford University and Deeplearning.ai - Coursera (2022) by Prof. Andrew NG

Awesome curated collection of images and prompts generated by GPT-4o and gpt-image-1. Explore AI generated visuals created with ChatGPT and Sora, showcasing OpenAI’s advanced image generation capabilities.

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

🦄🦄🦄AI赋能股票分析：AI加持的股票分析/选股工具。股票行情获取，AI热点资讯分析，AI资金/财务分析，涨跌报警推送。支持A股，港股，美股。支持市场整体/个股情绪分析，AI辅助选股等。数据全部保留在本地。支持DeepSeek，OpenAI， Ollama，LMStudio，AnythingLLM，硅基流动，火山方舟，阿里云百炼等平台或模型。

告别枯燥，致力于打造 Python 实用小例子，更多Python良心教程见 https://ai-jupyter.com

Memory library for building stateful agents

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

Transcribe on your own!

Evidently is ​​an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.

OpenMMLab Pose Estimation Toolbox and Benchmark.

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

Building a quick conversation-based search demo with Lepton AI.

Code for the paper "Jukebox: A Generative Model for Music"

Coroot is an open-source observability and APM tool with AI-powered Root Cause Analysis. It combines metrics, logs, traces, continuous profiling, and SLO-based alerting with predefined dashboards and inspections.

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,Minimax H3,...) inference in pure C/C++

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

Run Stable Diffusion on Mac natively

我的 ComfyUI 工作流合集 | My ComfyUI workflows collection

22 prompt engineering techniques with hands-on Jupyter Notebook tutorials, from fundamental concepts to advanced strategies for leveraging LLMs.

Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

end to end app store screenshot creation using AI

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

fast-stable-diffusion + DreamBooth

Scan, index, and archive all of your paper documents

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

A roadmap connecting many of the most important concepts in machine learning, how to learn them and what tools to use to perform them.

Minimal web UI for ChatGPT.

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

dsh-purge Community · DeepSeek Harness 社区维护版：宿主兼容、状态诊断、提示词管理、更新与本机备份回滚。基于小杨 / YuJunZhiXue 的 dsh-purge。

An EVM compatible Substrate chain, powered by StorageHub and secured by EigenLayer

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

A faster pytorch implementation of faster r-cnn

Experience, Learn and Code the latest breakthrough innovations with Microsoft AI