awesome-infra-for-ai digest (2026-07-13)

The awesome-infra-for-ai list received 7 new repositories. xLLM-AI/xllm (1,467 stars) — xLLM is a high-performance LLM inference engine optimized for diverse AI accelerators, particularly Chinese hardware, focusing on efficient, low-latency, and high-throughput model serving. mozilla-ai/otari (270 stars) — Otari is an open-source, OpenAI-compatible LLM gateway that centralizes routing, authentication, budget enforcement, and usage tracking for over 40 AI providers. muxi-ai/muxi (267 stars) — MUXI is an open-source AI application server providing production infrastructure for deploying and operating AI agents with built-in orchestration, memory, observability, and scaling capabilities. zhongkaifu/TensorSharp (209 stars) — TensorSharp is a native .NET inference engine specifically designed for serving GGUF large language models (LLMs) and DiffusionGemma-style text-diffusion models, offering console, web-based, and Op... edgee-ai/edgee (115 stars) — Edgee is an open-source, Rust-powered LLM gateway that optimizes AI traffic through token compression, multi-provider routing, and real-time observability. jigjoy-ai/mozaik (107 stars) — Mozaik is a TypeScript runtime for building self-organizing AI agents, enabling them to communicate, coordinate, and adapt at runtime rather than relying on fixed workflows. pmady/keda-gpu-scaler (106 stars) — A KEDA External Scaler that enables Kubernetes to autoscale GPU workloads by directly using NVIDIA NVML metrics, supporting scale-to-zero for AI inference servers like vLLM and Triton.