OpenFGA

Google Zanzibar-inspired authorization database

SpiceDB is an open-source authorization database inspired by Google's Zanzibar system, providing relationship-based access control (ReBAC) at scale. It defines permissions through a schema language that models relationships between users, resources, and roles, then evaluates authorization checks in single-digit milliseconds. Used by companies like Netflix and GitHub, SpiceDB handles millions of permission checks per second.

Modular open-source identity infrastructure with Kratos, Hydra, and Keto

Ory provides a suite of modular open-source identity components: Kratos for user management and authentication, Hydra for OAuth2 and OIDC, Oathkeeper for API gateway authorization, and Keto for fine-grained permission management. Used by OpenAI and other major organizations. API-first design with Go-based microservices that deploy independently or together as Ory Network cloud.

Heterogeneous CPU-GPU inference and SFT for large MoE models

Open-source framework for running and fine-tuning large Mixture-of-Experts models with heterogeneous CPU-GPU execution, optimized kernels, limited VRAM and SGLang or LLaMA-Factory integrations.

Official Kubernetes and Helm reference stack built on the vLLM inference engine

Official vLLM reference implementation for scaling the existing inference engine on Kubernetes with Helm, request routing, KV-cache offload, autoscaling and Prometheus/Grafana observability.

Distributed inference orchestration above vLLM, SGLang and TensorRT-LLM

Open-source, datacenter-scale orchestration layer that coordinates vLLM, SGLang and TensorRT-LLM across nodes with disaggregated serving, KV-aware routing, multi-tier cache management and automatic scaling.

Open-source GPU control plane for scalable AI model serving

Open-source GPU cluster manager that configures vLLM, SGLang, TensorRT-LLM or custom engines, serves models through compatible APIs, and provisions SSH-accessible GPU instances across on-premises, Kubernetes and cloud environments.

Disaggregated KV cache storage and transfer for LLM serving

Open-source infrastructure for disaggregated LLM serving that pools KV caches across prefill and decode workers, with high-performance transfer, distributed storage and integrations for vLLM and SGLang.

Reusable KV cache infrastructure for scalable LLM inference

Open-source KV cache management layer that persists, offloads and reuses model key-value caches across requests and serving engines to reduce repeated prefill work and improve inference throughput.