Lists (1)
Starred repositories
Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, optional RouterOS switch monitoring, and per-model decode/prefill/…
Monitoring + control dashboard for a sparkrun DGX Spark cluster: Ray/vLLM/recipe status and per-node vitals, plus admin-gated model preload, TLS management, live vLLM logs, and recipe start/stop/re…
Real-time hardware and LLM inference monitoring — GPU, CPU, memory, and vLLM metrics streamed to a dashboard.
Forces the bios settings to power on boot for headless DGX Spark (Works on all variants)
Serve inclusionAI/Ling-3.0-flash-int4 with SGLang in Docker on a DGX Spark (GB10) - start.sh / stop.sh
Cezar is a parallel coding agents orchestrator. Type a task, pick a workflow and an agent — Claude Code, Codex or OpenCode, or a mix of them per step — and watch it work live: steps, tool calls ...…
Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache
Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.
A persistent workspace for development work that self-improves and continues beyond one session.
top-style TUI for monitoring AI coding agent sessions
Local-first memory for AI coding agents. Indexes your repo and delivers bounded, provenance-backed context with drift checks and strict safety controls. No cloud, no API keys.
DeepSeek-v4-Flash-One-DGX-Spark - DwarfStar 4 Engine
Production-ready vLLM deployment wrapper for Qwen3.6-27B (NVFP4) — self-hosted OpenAI-compatible inference
Qwen3.6-27B (NVFP4) DFlash for DGX Spark
OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
Local-first live command center for Grok Build — runtime, ACP control, session history, and Git changes.
OpenFPM: A scalable open framework for particle and particle-mesh codes on parallel computers
Fine-tune LLMs on an AMD GPU on Windows via DirectML — no NVIDIA, no ROCm, no dual boot. Proven with a Mistral-7B LoRA fine-tune through Axolotl on a Radeon RX 7700 XT.
External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback.
Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.
Prompts for our Grok chat assistant and the `@grok` bot on X.
Your Personal AI super intelligence. A brain that builds a local-first memory of your life, a fantastic orchestrator of agent fleets and workflows, and a deep researcher.
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.