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
78,850 visible repositories in the index
1,201–1,224 of 3,965 · 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.
Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.
- ai-agents
- claude-code
- cursor
- langchain
Learning in infinite dimension with neural operators.
- neural-operator
- neural-operators
- partial-differential-equations
- pytorch
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)
Mastering Diverse Domains through World Models
Command line driven CI frontend and development task automation tool.
- testing
- python
- virtualenv
- continuous-integration
Snips Python library to extract meaning from text
- nlp
- nlu
- python
- machine-learning
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股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。
Hook and simulate global keyboard events on Windows and Linux.
- python
- keyboard-events
- keyboard-hooks
- keyboard-state
RAG that intelligently adapts to your use case, data, and queries
For GGUF support, see KoboldCPP: https://github.com/LostRuins/koboldcpp
A highly specialized reverse-engineering pipeline designed to structurally transplant original Vanilla character models into the EverQuest Online Adventures: Frontiers (PS2) game engine, resolving complex Vector Unit 1 (VU1) shader bugs, Emotion Engine (EE) memory overflows, and PS2 CDVDman hardware faults.
- assets
- eqoa
- eqoa-frontiers
- game
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
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
- diffusion-models
- flux
- genai
- lora