[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.
- computer-use
- vision-language-action
- vision-language-model
- agent
89,572 visible repositories in the index
2,377–2,400 of 4,644 · Most stars
[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.
DeepIE: Deep Learning for Information Extraction
这个项目记录了个人订阅的一些科技人的Blog地址,欢迎大家推荐,一起来完善! 欢迎自荐......
An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.
A simple python library to interact with Microsoft Graph and Office 365 API
A pytorch-based deep learning framework for multi-modal 2D/3D medical image segmentation
Python package and backend for the Elysia platform app.
Gaussian processes in TensorFlow
Retrying is an Apache 2.0 licensed general-purpose retrying library, written in Python, to simplify the task of adding retry behavior to just about anything.
Just a Bunch Of Plex Scripts
💫 Models for the spaCy Natural Language Processing (NLP) library
Publications from Trail of Bits
The Future of Data Engineering — A CLI SQL client for the modern data stack, enabling AI-native context engineering for data.
hacking-tool termux-tools termux noob-friendly instagram-bot bruteforce-password-cracker wordlist-technique
Django email backends and webhooks for Amazon SES, Brevo, MailerSend, Mailgun, Mailjet, Mailtrap, Postmark, Postal, Resend, Scaleway TEM, SendGrid, SparkPost, Unisender Go and more
Command line utility for forced alignment using Kaldi
Check if phone numbers are connected to Telegram accounts.
LXMF client for Android, Linux and macOS allowing you to communicate with people or LXMF-compatible systems over Reticulum networks using LoRa, Packet Radio, WiFi, I2P, or anything else Reticulum supports.
Benchmark for tracking model capability after release.
fastdup is a powerful, free tool designed to rapidly generate valuable insights from image and video datasets. It helps enhance the quality of both images and labels, while significantly reducing data operation costs, all with unmatched scalability.
A powerful no-code automation tool. Build workflows via drag-and-drop modules for web scraping, form filling and automated testing. | 一款功能强大的自动化工具,通过拖拽模块的方式快速构建自动化工作流,无需编写任何代码即可实现网页数据采集、表单填写、自动化测试等任务。【QQ交流群:115069513】
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.
Large-scale LLM inference engine
📇 Synchronize calendars and contacts.