AI 开源项目榜。
Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.
Data science, machine learning, and web development project code for https://www.youtube.com/c/Dataquestio .
A high performance 3DGS renderer
This repo is specially created for all the work done my me as a part of Coursera's Machine Learning Course.
A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.
Finding the genre of a song with Deep Learning
[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs
Build realtime AI voice agents using FastRTC for low-latency streaming, Superlinked for vector search, Twilio for live phone calls, and Runpod for scalable GPU deployment.
Deep Learning Interview 深度学习面试题目汇总
Build AI applications that can see, hear, and speak using your screens, microphones, and cameras as inputs.
Build plugins that feel like native, first-class features of ChatGPT.
A JAX-based simulator for autonomous driving research.
Learning Deep Representations of Data Distributions
Autonomous ground robots (2WD, 4WD, Ackermann Steering, Mecanum Drive)
Turn your OpenClaw into a Chief of Staff
Sample code for Google Cloud Vision
Autonomous software factory. Give it a GitHub issue, a spec or a one-line task; get back a pull request with a signed receipt anyone can re-check offline. Runs on your machine with your own keys: Claude, Codex, OpenCode.
Unofficial OpenClaw runbook for running agents day to day without burning money, exposing your gateway, or trusting random automation.
人味儿写作 · An AI agent skill: edit people's words without erasing the person behind them
The open-source iOS app that's making quality voice transcription more accessible on mobile devices.
Benchmarking Deep Learning operations on different hardware
A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".
CodeStable 是一套面向严肃软件工程、坚持人在环的 AI 编码工作流。它不以编排 Agent 为中心，而是组织需求、架构、特性、问题与历史决策，让 Codex 和 Claude 驱动的开发过程可控、可追溯、可持续演进。
Configs and boilerplates for Label Studio's Machine Learning backend
[CVPR 2021 & IJCV 2024] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Bringing the power of MCP to the web
Read Pilot analyzes online articles and generate Q&A cards for you. Powered by OpenAI & Next.js.
A library created to revitalize C++ as a machine learning front end. Per aspera ad astra.
Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction