Starred repositories
KAI Scheduler is an open source Kubernetes Native scheduler for AI workloads at large scale
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
eBPF LSM based Mandatory Access Control and jailer
Open-source plugin for designing and reviewing software with agents
Policy-driven, layered isolation and containment
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
Make Pi sessions feel endless
A treemap for finding and removing what fills your disk, for Omarchy. Rust + GPUI.
NVIDIA GPU Operator creates, configures, and manages GPUs in Kubernetes
NVSentinel detects and remediates GPU faults on Kubernetes nodes
The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, …
A toolkit for discovering cluster network topology.
A straightforward method for training your LLM, from downloading data to generating text.
Run:ai is the AI workload orchestration platform for Kubernetes. This monorepo contains the control plane services, in-cluster Kubernetes operator/controllers, shared libraries and clients, the ins…
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a scale faster than an LLM, with a calibrated confidence on every decision.
Brig: run coding agents in a microVM sandbox - the Go cli (brig) and session daemon (brigd)
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.
A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.
Tooling for optimized, validated, and reproducible GPU-accelerated AI runtime in Kubernetes
A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
Simple, unified interface to multiple Generative AI providers