Docker compose serving stack for DeepSeek v4 Flash DSpark for NVIDIA Spark GB10 system using Aidendle94 image

Docker configuration for running VLLM on dual DGX Sparks

Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, and structured output. Supports vLLM, LiteLLM, and llama.cpp.

Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models

The open source coding agent.

A simple dashboard to track OpenCode + Oh-My-Opencode agents

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Light, fluffy, and always free - The AWS Local Emulator alternative

Web dashboard for llama-benchy benchmarks. Consumes the --emit-progress JSONL stream and streams live ViewModel snapshots to the browser over Server-Sent Events.

The agent that grows with you

Pure Rust Inference Engine

A curated list of awesome plugins, themes, agents, projects, and resources for https://opencode.ai

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…

AEON vLLM Ultimate — vLLM 0.24.0 built from source for DGX Spark / Blackwell (sm_121a/GB10). One image serves the whole AEON fleet (Gemma-4-26B-A4B, Qwen3.6-27B, Qwen3.6-35B-A3B) with DFlash specul…

Collection of step-by-step playbooks for setting up AI/ML workloads on NVIDIA DGX Spark devices with Blackwell architecture.

NVIDIA capability registry and Spark-aware routing layer for Hermes Agent and NemoClaw users

Post-quantum endpoint-to-endpoint encryption for messaging, file-sharing, and secret remote file storage SDK

Build Better Websites. Create modern, resilient user experiences with web fundamentals.

Official electron build of draw.io

A complete Azure Virtual Desktop deployment solution focused on compatibility across all clouds used by US Government customers.

A modern X11 server written from scratch in Rust.

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

Build and run containers leveraging NVIDIA GPUs

cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign languag…

draw.io is a JavaScript, client-side editor for general diagramming.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

A high-efficiency Flash model for real-world agents.

Model Shelf is a local-first model resolver that helps AI agents and scripts find model weights on your own storage before downloading from Hugging Face. Point it at an internal SSD, NAS, external …

A vim plugin for syntax highlighting Ansible's common filetypes