Like Manus, Computer Use Agent(CUA) and Omniparser, we are computer-using agents.AI-driven local automation assistant that uses natural language to make computers work by themselves
Repository Index
82,088 visible repositories in the index
1,345–1,368 of 4,998 · Most stars
Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's WaveNet and tensorflow
A simple, easy-to-hack GraphRAG implementation
Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you already use.
- multi-object-tracking
- sort
- bytetrack
- oc-sort
A collection of loss functions for medical image segmentation
Official tensorflow implementation for CVPR2020 paper “Learning to Cartoonize Using White-box Cartoon Representations”
Differentiable architecture search for convolutional and recurrent networks
- deep-learning
- automl
- image-classification
- language-modeling
StarCraft II Client - protocol definitions used to communicate with StarCraft II.
Learning in infinite dimension with neural operators.
- neural-operator
- neural-operators
- partial-differential-equations
- pytorch
Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.
A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型
- albert
- bert
- roberta
- xlnet
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
Expert code review skill: SOLID, security, performance, error handling, boundary conditions
Domain-fronted HTTP/SOCKS5 proxy tunneling traffic through Google Apps Script with MITM TLS interception, HTTP/1-2 multiplexing, and DPI evasion.
Command line driven CI frontend and development task automation tool.
- testing
- python
- virtualenv
- continuous-integration
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
Ethereum Consensus Specifications
Windrecorder is a memory search app by records everything on your screen in small size, to let you rewind what you have seen, query through OCR text or image description, and get activity statistics, like Microsoft's Windows Recall or Rewind.
- ffmpeg
- streamlit
- productivity
- rewind
Visual profiler for Python
- python
- visualization
- profiler
- developer-tools
Snips Python library to extract meaning from text
- nlp
- nlu
- python
- machine-learning
A terminal application to view, tail, merge, and search log files (plus JSONL).
- jsonl
- rich
- terminal
- terminal-based
Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""
- code-generation
- flow-engineering
- paper-implementations
- state-of-the-art
Connect any AI copilot or autonomous agent to your enterprise tools — through a single, secure MCP/Agent gateway with built-in identity, access control, and full observability.
State-of-the-art LLM compression, built for production inference with vLLM
- compression
- quantization