Repo đang lênCập nhật hằng ngày từ GitHub

Introducing the Assistant Swarm. An extension to the OpenAI Node SDK to automatically delegate work to any assistant you create in OpenAi through one united interface and manager. Now you can delegate work to a swarm of assistant all specialized with specific tasks you define.

Paving the way for open agents and AGI for all.

Next-generation Video instance recognition framework on top of Detectron2 which supports InstMove (CVPR 2023), SeqFormer(ECCV Oral), and IDOL(ECCV Oral))

Image Acquisition Library for GenICam-based Machine Vision System

[TIP2026] Official codes of CCSRv2 and CCSRv1: Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution

An implementation of 1D, 2D, and 3D positional encoding in Pytorch and TensorFlow

DiffSharp: Differentiable Functional Programming

Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019

NextPlaid, ColGREP: Multi-vector search, from database to coding agents.

RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.

MDA Open Spec — a Markdown superset for agent-facing documents. One .mda source compiles to drop-in SKILL.md, AGENTS.md, MCP-SERVER.md, and CLAUDE.md. JSON Schema validated, with typed dependency graph, footnote relationships, and Sigstore-anchored signatures. For agentskills.io and AAIF runtimes.

A simple and beautiful cross-platform screenshot software, It also supports OCR, image translation, stickers and pinning images features. | 简单且漂亮的跨平台截图软件，支持离线 OCR、图片翻译、贴图和钉图等功能

A list of tools for annotating data, managing annotations, etc.

Efficiently Scaling Up Video Annotation with Crowdsourced Marketplaces. IJCV 2012

FlashAttention (Metal Port)

A browser extension to display ChatGPT response alongside Search Engine results

Python library for analysing faces using PyTorch

⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.

Open-source design agent: on-brand stills, decks, diagrams, charts and motion graphics from a chat thread, built on Deep Agents.

Professional deep research report generation Skill — one command, ten minutes, broker-grade deep research / 深度调研报告生成 Skill — 一条命令，十分钟出券商级深度调研报告

Control Figma from the command line. Full read/write access for AI agents — create shapes, text, components, set styles, export images. 100+ commands.

[ACL 2026 Oral] "LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"

ScreenAgent: A Computer Control Agent Driven by Visual Language Large Model (IJCAI-24)

multilspy is a lsp client library in Python intended to be used to build applications around language servers.

Image Super-Resolution Using Deep Convolutional Networks in Tensorflow https://arxiv.org/abs/1501.00092v3

A wechat robot based on ChatGPT with no risk, very stable! 🚀

Code-Native Data Privacy

ApplicationInsights-dotnet

High frequency trading (HFT) framework built for futures using machine learning and deep learning techniques

ThunderID, an LF Decentralized Trust project, is a high-performance, open-source identity stack designed for developers to secure and manage access for humans, AI agents, and machines through fully composable identity flows.

Agentic SDLC infrastructure. Define guardrails. Collect signals. Enforce continuously. Signed records of what your AI coding agents and CI/CD pipelines did, checked against policies as code, with the loop closed in CI/CD. AI sessions, SBOMs, VEX, SARIF and SLSA provenance, built on Sigstore and in-toto. Apache 2.0.

🔴 VERY LARGE AI TOOL LIST! 🔴 Curated list of AI Tools - Updated 2026

Cross-platform SDK for facial motion capture producing blendshapes and rigid head poses in 3D space in realtime from photos or videos.

[CVPR 2025] RollingDepth: Video Depth without Video Models

This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" (https://arxiv.org/abs/1911.10194)

🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox

The world's cleanest AutoML library ✨ - Do hyperparameter tuning with the right pipeline abstractions to write clean deep learning production pipelines. Let your pipeline steps have hyperparameter spaces. Design steps in your pipeline like components. Compatible with Scikit-Learn, TensorFlow, and most other libraries, frameworks and MLOps environments.

《动手学深度学习》习题解答，在线阅读地址如下：

Notes for Deep Learning Specialization Courses led by Andrew Ng.

kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)

中文Mixtral混合专家大模型（Chinese Mixtral MoE LLMs）

OBBDetection is an oriented object detection library, which is based on MMdetection.

Anthropics/skills中文学习版本 来自：https://github.com/anthropics/skills

CLI to install, manage & troubleshoot Kubernetes clusters running Cilium

PyTorch implementation of Neural Combinatorial Optimization with Reinforcement Learning https://arxiv.org/abs/1611.09940

Neural Turing Machines (NTM) - PyTorch Implementation

DeepSeek API pricing guide for models, cache hits, and peak hours (2026).

XRAG: eXamining the Core - Benchmarking Foundational Component Modules in Advanced Retrieval-Augmented Generation

Chain together LLMs for reasoning & orchestrate multiple large models for accomplishing complex tasks