Lists (3)
Stars
GoodbyeDPI — Deep Packet Inspection circumvention utility (for Windows)
From expressive code to powerful GUIs in no time: a fast, feature-rich, cross-platform toolkit for C++ & Python.
[ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents
The first open-source Artificial Narrow Intelligence generalist agentic framework Computer-Using-Agent that fully operates graphical-user-interfaces (GUIs) by using only natural language. Uses Visu…
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Implementation of the ScreenAI model from the paper: "A Vision-Language Model for UI and Infographics Understanding"
Dear ImGui: Bloat-free Graphical User interface for C++ with minimal dependencies
Keep passwords and other sensitive information out of your inboxes and chat logs.
[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).
A JavaScript / TypeScript / Python / C# / PHP / Go cryptocurrency trading API with support for more than 100 bitcoin/altcoin exchanges
Python library, which allows you to automate Google Chrome browser.
Training and serving large-scale neural networks with auto parallelization.
VRT: A Video Restoration Transformer (official repository)
A Python implementation of global optimization with gaussian processes.
State-of-the-art 2D and 3D Face Analysis Project
Code for the paper "Language Models are Unsupervised Multitask Learners"
Hundreds of Kerbals were killed in the making of this mod.
YoloV3 Implemented in Tensorflow 2.0
Sample applications for the Cinder framework
Spiral galaxy simulator using the density wave theory