#nvidia

Lightweight self-hosted NVIDIA GPU fleet monitoring with read-only agents, secure ingestion, compressed storage, and a responsive React dashboard.

给别人的 Agent 做体检的评测 Agent：本地三家族裁判打分、分歧交云端仲裁、badcase 聚类、证据卡片、pass^3 回归 | 第三届 NVIDIA DGX Spark 黑客松 · 能工智人5X

Open hardware desktop AI node: 4× Tesla V100, 128GB HBM2, PCIe/NVLink topology and V-Core liquid/air cooling.

Reproducible token-throughput benchmark for OpenAI-compatible LLM servers, tuned for NVIDIA Spark and GB10 inference.

Production-oriented Kimi K3 inference control plane with checkpoint release gates, MoE capacity planning, OpenAI gateway, NVL72 deployment, benchmarks, and observability.

⚡ Autonomous Software Testing & Repair Agent powered by NVIDIA Nemotron on Nebius Token Factory (Nebius x NVIDIA Hackathon)

Local-model gateway for Claude Code, Zoo Code, and Kilo: route AI coding agents through llama.cpp/Ollama/vLLM on Distrobox. No API keys, no cloud fallback, nothing auto-starts - local mode either works or fails cleanly. Classic LiteLLM proxy, or the optional single-provider Kilo mode.

GPU-accelerated Manim workspace + 14 Agent Skills + a 5,523-symbol offline API index, so coding agents can drive Manim as an API instead of guessing. NVENC encoding via a PyAV patch, ManimCE 0.21 and ManimGL/wgpu side by side, reproducible benchmarks, and verified corrections to widely-repeated docs.

Nigeria remittance timing agent (Nebius × NVIDIA Best Apps track).

NVIDIA DGX Spark power user and edge AI maximizer

MindFoundry — NemoClaw-secured long agent for NVIDIA Agent Hackathon. Builds AI replicants of your teammates and answers ops questions with cited Nemotron synthesis.

Serve DeepSeek and Qwen, run an on-demand model library, and fine-tune with Unsloth QLoRA on 2x NVIDIA DGX Spark. TP=2 vLLM lanes behind one OpenAI-compatible endpoint for OpenCode, Cursor, and Hermes. Honest benchmarks, committed artifacts.