Havuz

NVIDIA NemoClaw, OpenClaw, Hermes ve LangChain Deep Agents Code ajanlarını NVIDIA OpenShell sandbox’larında çalıştırmak için kurulum, inference yönetimi ve güvenlik politikaları sağlayan bir stack’tir.

Neden yükseliyor · 196 günde 22 bini aşan yıldız ve son 28 gündeki 751 commit ile 20 farklı yazar, güçlü ilgi ve yüksek geliştirme temposuna işaret ediyor. Agent güvenliği güncel ve gerçek bir ihtiyaç; NVIDIA markası ile birden fazla agent entegrasyonu da görünürlüğünü artırıyor. Ancak bu ölçüler tek başına üretim olgunluğunu veya güvenlik etkinliğini kanıtlamaz.

Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and how

Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, NVID

Self-hosted vLLM made simple. Git-friendly YAML for models and profiles, full lifecycle from an intuitive CLI and TUI.

Distributed image and video generation in ComfyUI for two NVIDIA DGX Sparks.

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decodi

NeMo Helix: Make the agents you ship faster, more accurate, and safer.

dgx-spark-qwen38 is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Ace

面向 DeepSeek Harness 的本地图像生成插件（优化版）：经本机 ComfyUI 调用 Qwen-Image 2.1 生成图像，全部流量限于 127.0.0.1。本版增强推理性能、NVIDIA/Intel/AMD 显卡适配与 Windows/Linux 兼容。原作者

Your adaptive AI agent for your work.

Self-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can ex

Real-time hardware and LLM inference monitoring — GPU, CPU, memory, and vLLM metrics streamed to a dashboard.

Your reading list, as a podcast you own

Self-hosted AI code review for GitHub pull requests.

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with N

OpenAI-compatible gateway aggregating 8 free LLM providers with automatic failover, circuit breakers, and smart routing. 32+ models, zero c

Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on

📊 Automated hourly benchmarks for 20+ NVIDIA NIM models — interactive dashboard, zero infra, self-hostable. Open-source & community-driven.

Dashboard for InferenceX™, Open Source Continuous Inference | InferenceX 仪表板

Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable

Qwen3.8-Flash-Next (180B MoE) on one 12-16 GB NVIDIA GPU, Linux or Windows. Own engine, own compression.

A tiered-memory system design for workloads that don't fit in RAM: measure the working set, pin the hot tier, stream the cold tier from flas

Free NVIDIA DLI course: build, coordinate, and secure AI agents with NemoClaw and OpenShell. Browser-based, no GPU required. Available in En

Hermes Agent (NousResearch) sandboxed by NVIDIA OpenShell — hardware-enforced network/filesystem/syscall policy, full memory + gateway stack

Local-first AI workbench for OCR, transcription, translation, image generation, mind maps and composable workflows. Built for DGX Spark.

Browser-based model and inference management for NVIDIA DGX Spark - inventory local and Hugging Face models, manage Ollama and LiteLLM, gene

Legacy: self-hosted LLM/RAG stack installer for DGX Spark (arm64). The work continued as AGmind Systems Lab — measured local-LLM performance

Local image generation and editing for NVIDIA DGX Spark, powered by Qwen-Image-2.1 and Gradio.

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simula

让 Codex 白嫖 NVIDIA 免费顶级模型，一键接入 | Transparent proxy between Codex and NVIDIA NIM — use NVIDIA's free hosted top-tier models with Codex

Zero-dependency Go proxy for rotating free-tier AI API keys. No more 429s.

Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract + two-phase Train→Nudge (silver-medal NVIDIA

DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding

CPU-side action routing, context compression, and causal memory for AI agents — matches an LLM-everything agent at 58% fewer LLM calls and ~

The ultimate memory backend for OpenClaw and Claude Code. Persistent conversation memory with LLM fact extraction, foundation-model rerankin

The visual compute platform for AI and robotics — connecting agents, GPU workloads, simulation, training, and real robots through typed work

Windows utility focused on cuda setup, nvidia local AI, and cuda environment for local AI workflows.

Object-storage-native KV cache for LLM inference & RL. Cross-restart, cross-conversation, cross-engine via shared S3 bucket.

Catch local LLMs spilling into the CPU. One run shows GPU placement, prefill, decode, memory, power and a verdict.

⚡ Adaptive multi-model LLM router — 80+ providers, Jev System One single-pass routing (model=jev-auto), pheromone-trail failover, parallel e

MCP server for NVIDIA GPU metrics give AI agents real-time access to GPU utilization, memory, temperature, and power

The old advice to avoid Windows for local LLMs used to be right. It isn't anymore. The fixes for display-GPU desktop crashes and WSL memory

Realtime TUI monitor for local LLM servers (ollama, llama.cpp). The only GPU monitor that knows what model is running and how much each toke

Automate ongoing market research with an AI planner, Jules agents, live conversations, and organized GitHub reports.

Docker compose configs for serving Qwen3.8-27B on a DGX Spark (GB10): vLLM+MTP current, SGLang+DSPARK + FP8 rollback stacks

See every GPU in your lab in the terminal, the browser or a report — who holds each GPU, which ones sit idle. One Python file, nothing to in

High-performance CUDA inference engine for Qwen models, written from scratch in C++/CUDA