Lists (8)
Starred repositories
The offline batch gateway is an llm-d compatible implementation of the OpenAI Batch inference API
2
Updated Jan 13, 2026
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Specification and documentation for the Universal Commerce Protocol (UCP)
A lightweight macOS menubar hub for your GitHub works.
Open-source, secure environment with real-world tools for enterprise-grade agents.
Model Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and improve overall performance.
Documentation repository for NVIDIA Cloud Native Technologies
A curated catalogue of awesome agentic AI patterns
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
A CUDA API interception library that simulates GPU devices in even non-GPU environments.
Rapid and cost-effective operator and best practice for agent sandbox lifecycle management.
Agentic networking policies and governance for agents and tools in Kubernetes
eBPF-powered Linux observability with AI incident detection. AGPL-3.0 licensed.
wentao.site / Hugo Template / A template repository for Hugo based blog
Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.
AGENTS.md — a simple, open format for guiding coding agents
NVIDIA GPU metrics exporter for Prometheus leveraging DCGM
DRANET is a Kubernetes Network Driver that uses Dynamic Resource Allocation (DRA) to deliver high-performance networking for demanding applications in Kubernetes.
Observability 3.0: AI-Powered APM = AI Stack + Observability Stack
vArmor is a cloud native container sandbox system based on AppArmor/BPF/Seccomp. It also includes multiple built-in protection rules that are ready to use out of the box.
统计 Git 项目的 commit 时间分布，进而推导出项目的编码工作强度。 Analyzes the commit time distribution of Git projects to infer coding work intensity.
This repository contains a Kubernetes controller that manages node taints based on multiple readiness conditions, providing fine-grained control over when nodes are ready to accept workloads.