Starred repositories
DeepSeek Harness: Everything is a Plugin.
The Prometheus monitoring system and time series database.
[CVPR2026]🚀🚀🚀Official code for the paper "YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection." *(YOLO = You Only Look Once)* 🔥🔥🔥
An agentic skills framework & software development methodology that works.
The open-source AI workbench for scientific research
Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision
The code for "InstructSAM: Segment Any Instance with Any Instructions"
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Use Claude Code, OpenCode, Cursor CLI, and Codex on mobile and web with CloudCLI (aka Claude Code UI). CloudCLI is a free open source webui/GUI that helps you manage your Claude Code session and pr…
This is a WebUI interface based on CLI-Proxy-API, designed to simplify configuration modifications and runtime status monitoring.
Algorithm powering the For You feed on X
Lightweight coding agent that runs in your terminal
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.
JoyAI-VL-Interaction: An Open Real-time Video-Language Interaction System
LibreYOLO is a MIT licensed open source computer vision library
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
Lightweight (7MB) Terminal-first AI-native dev workspace
[ECCV 2026] RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models
A lightweight all-in-one terminal with 20+ protocols — SSH, RDP, SFTP, databases, Kubernetes and more. With a built-in autonomous AI Agent that plans and runs multi-turn shell commands.
Vision as Unified Multimodal Generation
[CVPR 2026] Scaling Spatial Intelligence with Multimodal Foundation Models
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.6 Series, Grok 4.5, Claude mod…
250+ Fine-tuning & RL Notebooks for text, vision, audio, embedding, TTS models.
TabFM (Tabular Foundation Model) is a pretrained tabular foundation model developed by Google Research for tabular data regression and classification.
Self-supervised learning for spatial perception
Model Context Protocol Servers
Open-Source Low-Latency Accelerated Linux WebRTC HTML5 Remote Desktop Streaming Platform for Self-Hosting, Containers, Kubernetes, or Cloud/HPC