Artem Matskevych Claim this profile

Codex CLI plugin: delegate reviews and bounded coding tasks to the local Grok Build CLI via a bundled MCP server

Reproducible kit to deploy DeepSeek-V4-Flash-DSpark on a 2× NVIDIA DGX Spark (GB10) cluster: vLLM TP=2 over QSFP 200GbE, NVFP4 KV, DSpark speculative decoding, 1M context, systemd self-heal. Apache-2.0.

Claude Code CLI marketplace for Codex and Grok Build reviews, second opinions, and bounded delegated tasks.

Serve poolside/Laguna-S-2.1-NVFP4 (117.6B MoE, 256K ctx, DFlash spec-decode) with vLLM on a single NVIDIA DGX Spark (GB10) — bare-metal, no sudo, systemd + watchdog, measured tuning recipe. Operated from a Mac over SSH.

Local-first developer workspace manager for consistent code namespaces, Git hydration, secrets, and AI agent worktrees.

Homebrew tap for DevStrap (brew install Reederey87/devstrap/devstrap)

Serve unsloth Qwen3.6-35B-A3B GGUF with a natively-built llama.cpp on an NVIDIA DGX Spark (GB10) — OpenAI-compatible endpoint, MTP speculative decoding, vision, systemd service.

Reproducible, hardened vLLM serving kit for nvidia/Qwen3.6-35B-A3B-NVFP4 on the NVIDIA DGX Spark (GB10 Grace Blackwell, SM121): OpenAI-compatible, MTP speculative decoding, tool-calling, plus eval + metrics helpers.

No description.

No description.

No description.

Build a Streaming Data Pipeline in Python