Repo đang lênCập nhật hằng ngày từ GitHub

Autonomous software factory. Give it a GitHub issue, a spec or a one-line task; get back a pull request with a signed receipt anyone can re-check offline. Runs on your machine with your own keys: Claude, Codex, OpenCode.

Based on GroundingDino and SAM, use semantic strings to segment any element in an image. The comfyui version of sd-webui-segment-anything.

Dapr quickstarts and tutorials: runnable C#, Go, Java, JavaScript and Python code for Dapr Workflow (durable execution), durable AI agents, pub/sub, state, actors, service invocation, jobs, bindings and more.

(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

Open-source ManyChat alternative, built for AI. Omnichannel marketing across WhatsApp, TikTok, Facebook, Instagram, Telegram, Zalo, Email, API, and Webchat 🤖

Simple. Scalable. Multi-cloud monitoring.

Precompiled packages for AWS Lambda

XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library

Finding the genre of a song with Deep Learning

[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs

🐙 The Go backend powering OCTO — an open workplace built for humans × AI agents. REST & WebSocket APIs, Lobster (AI agent) orchestration, and WuKongIM real-time messaging control plane.

Cotabby is local AI autocomplete for your entire Mac. Open source. On device. Everywhere you type.

Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.

Read Pilot analyzes online articles and generate Q&A cards for you. Powered by OpenAI & Next.js.

Lightweight, useful implementation of conformal prediction on real data.

100+ LLM interview questions with answers.

A fast, multi-threaded Redis® and Valkey alternative written in Rust: drop-in compatible, with full-text and vector search built in

Deep Learning Interview 深度学习面试题目汇总

Unofficial OpenClaw runbook for running agents day to day without burning money, exposing your gateway, or trusting random automation.

A collection of resources on controllable generation with text-to-image diffusion models.

全网最全的、持续更新的、最火爆的 100+ 人格 蒸馏skills 合集｜ 多agent系统 ｜名人/导演/天涯大神/古籍/二次元/职场/情感全品类

开源的 AI 订阅价格聚合与比价平台，收录 ChatGPT、Claude、Gemini、Grok、Cursor 等产品的官方订阅价格和卡网渠道报价，帮助用户快速查询并比较不同购买渠道。

🐙 关于提示词工程（prompt）的指南、论文、讲座、笔记本和资源大全（自动持续更新）

OpenAI Gym environments for an open-source quadruped robot (SpotMicro)

AI-powered Jupyter Notebook. Use AI to generate and edit code cells, automatically fix errors, and chat with your data

PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations

A library created to revitalize C++ as a machine learning front end. Per aspera ad astra.

Compare the performance of different LLM that can be deployed locally on consumer hardware. Run yourself with Colab WebUI.

A deep dive into embeddings starting from fundamentals

Formula Recognition & Office Editing | Handwriting & PDF to LaTeX/Markdown | Secure API Integrations.

Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;

OCR engine for all the languages

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.

Paddle.js is a web project for Baidu PaddlePaddle, which is an open source deep learning framework running in the browser. Paddle.js can either load a pre-trained model, or transforming a model from paddle-hub with model transforming tools provided by Paddle.js. It could run in every browser with WebGL/WebGPU/WebAssembly supported. It could also run in Baidu Smartprogram and WX miniprogram.

Riemannian Adaptive Optimization Methods with pytorch optim

T3Bench: Benchmarking Current Progress in Text-to-3D Generation

Comark is an open-source Markdown parser and renderer with components, attributes and plugins. It streams AI output to React, Vue, Svelte, Angular, HTML and the terminal.

🔎 Search the information available on a webpage using natural language instead of an exact string match.

《AI 研发提效：自己动手训练 LoRA》，包含 Llama （Alpaca LoRA）模型、ChatGLM （ChatGLM Tuning）相关 Lora 的训练。训练内容：用户故事生成、测试代码生成、代码辅助生成、文本转 SQL、文本生成代码……

Implementation of Quickdraw - an online game developed by Google

Real time WebGL and JavaScript library for face tracking, expression detection and animated emoticons in the browser, with both SVG and Three.js demos included 😄

PyTorch re-implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC datasets

Simple transformer implementation from scratch in pytorch. (archival, latest version on codeberg)

Open-core workflow engine powering Bubble Lab — and fully runnable, hostable, and extensible on its own.

Implementation of TabTransformer, attention network for tabular data, in Pytorch

Streamlit Component, for a Chatbot UI

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation

Inference code and configs for the ReplitLM model family

LLM-based ontological extraction tools, including SPIRES