Transaction Tokens (RFC 8693) for Kubernetes — seal identity, context, and authorization across multi-hop agent workflows via AgentGateway + ext_authz.

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

Claude Code skill that removes signs of AI-generated writing from text

The best-benchmarked open-source AI memory system. And it's free.

llm-d benchmark scripts and tooling

Tooling for optimized, validated, and reproducible GPU-accelerated AI runtime in Kubernetes

A cloud-agnostic Kubernetes node autoscaler that dynamically scales infrastructure across Azure and emerging neoclouds like Nebius—managed from a single control plane.

Rally your AI squad to GitHub issues and PRs via git worktrees

💫 Toolkit to help you get started with Spec-Driven Development

Inspektor Gadget is a set of tools and framework for data collection and system inspection on Kubernetes clusters and Linux hosts using eBPF

✈️ Kubernetes-native platform for deploying and managing AI inference across multiple providers

Discover ingress-nginx usage and auto-generate Gateway API migration plans before ingress-nginx reaches end-of-life (March 2026).

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).

The best ChatGPT that $100 can buy.

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

A sample pack of GitHub Agentic Workflows!

Achieve state of the art inference performance with modern accelerators on Kubernetes

Wassette: A security-oriented runtime that runs WebAssembly Components via MCP

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Next Generation Agentic Proxy for AI Agents and MCP servers

LLM inference in C/C++

Home of the out-of-tree KAITO plugin for Headlamp Kubernetes UI

The Security Toolkit for LLM Interactions

Set of tools to assess and improve LLM security.

A comprehensive social media management tool designed to help you create, format, and post content across multiple platforms including LinkedIn, Twitter/X, Bluesky, and Mastodon. Features advanced …

Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton

CRIU based GPU workload migration in Kubernetes

OPA Gatekeeper provider for GitHub Artifact Attestations