Repo đang lênCập nhật hằng ngày từ GitHub

The ultimate collection of APIs for building autonomous AI agents — 2,036 production-ready APIs across Agents, AI Models, and MCP Servers. Stop wasting weeks building infrastructure. Plug these in and ship your agent today.

A language-agnostic interface to TensorBoard

Keras version of Realtime Multi-Person Pose Estimation project

DeepSeek Harness 启动器：启动项与多实例，版本、插件、整合包、MCP 和技能管理。A DeepSeek Harness launcher: launch entries, multiple instances, versions, plugins, modpacks, MCP and skills.

[CVPR 2024] FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation

Precise RoI Pooling with coordinate gradient support, proposed in the paper "Acquisition of Localization Confidence for Accurate Object Detection" (https://arxiv.org/abs/1807.11590).

Using Gemini in ComfyUI

Inverse RL algorithms (APP, MaxEnt, GAIL, VAIL)

An Open-Source Package for Textual Adversarial Attack.

PyTorch code for "PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer" (CVPR 2020 Oral)

A deep neural network that learns to drive in video games

An LLM extension for Ghidra to enable AI assistance in RE.

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

[CVPR 2020] CenterMask : Real-Time Anchor-Free Instance Segmentation

A Python package to stabilize videos using OpenCV

🌮 Trash Annotations in Context Dataset Toolkit

Learn any journal's writing conventions from its published papers, then revise your manuscript to match — section by section.

[CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing

A curated list of applied machine learning and data science notebooks and libraries across different industries.

Small, dependency-free, fast Python package to infer binary file types checking the magic numbers signature

[CVPR26] TESSERA is a foundation model that can process time-series satellite imagery for applications such as land classification and canopy height prediction. Developed at the University of Cambridge, it enables efficient extraction of temporal patterns from Earth observation

If you can read ~100 lines of Python, you understand agents.

Open-source OCR and dictionary tool.

SkyWalking RocketBot UI

A sign language interpreter using live video feed from the camera.

ML powered analytics engine for outlier detection and root cause analysis.

A collection of deep learning based RGB-T-Fusion methods, codes, and datasets. The main directions involved are Multispectral Pedestrian Detection, RGB-T Aerial Object Detection, RGB-T Semantic Segmentation, RGB-T Crowd Counting, RGB-T Fusion Tracking.

Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate

An elegant interactive CLI for ChatGPT

[CVPR 2020] CenterMask : Real-time Anchor-Free Instance Segmentation

AI-Video-Cropper is a Python-based tool that leverages the power of GPT-4 (OpenAI's language model) to automatically analyze videos, extract the most interesting sections, and crop them for improved viewing experience. This project combines the capabilities of GPT-4, FFmpeg, and OpenCV to automate the process of identifying highlights in videos

基于JDK8 AI 聊天机器人！微信公众号 Midjourney画图、卡密兑换、web 支持ChatGPT、Midjourney画图、sd画图，卡密兑换，易支付，公众号引流，邮件注册🔥

微信风格的 ChatGPT，使用 Next.js 构建，私有化部署的最佳选择！

PyTorch Implementations for DeeplabV3 and PSPNet

Machine Learning inference engine for Microcontrollers and Embedded devices

Embeddable version control system for files and tables.

Large Context Attention

An Innovative Agent Framework Driven by KG Engine

[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"

Find zero-days while you sleep. DeepZero is an automated vulnerability research framework that parses, decompiles, and analyzes thousands of Windows kernel drivers for exploitable IOCTLs natively using AI agents.

🎮 Real-time Game Translation Tool | OCR + AI Translation | Windows Gaming | Open Source

Code for finetuning AlexNet in TensorFlow >= 1.2rc0

SkyAGI: Emerging human-behavior simulation capability in LLM

LLM-maintained personal knowledge base for Obsidian. Based on Andrej Karpathy's LLM Wiki pattern.

Model Predictive Path Integral (MPPI) with approximate dynamics implemented in pytorch

A curated list of papers dedicated to neural text (semantic) matching.

Network Intrusion Detection KDDCup '99', NSL-KDD and UNSW-NB15

Example notebooks for working with SageMaker Studio Lab. Sign up for an account at the link below!

The open source Meme Search Engine and Finder. Free and built to self-host locally with Python, Ruby, and Docker.

Stash — persistent memory layer for AI agents. Episodes, facts, and working context stored in Postgres. MCP server included. Self-hosted, single binary, no cloud required.