gputaskman: See What’s Eating Your GPU Memory Now
Scott Hanselman's open-source gputaskman shows per-process VRAM, LLM model weights, and KV-cache breakdowns. The GPU monitor your local AI workflow actually needs.
Vercel eve 1.0 RC6: Build Durable AI Agents as Directories of Files
Vercel shipped eve 1.0 RC6 on November 5, and if you’ve been watching the agent ...
Wiki.js 3.0: Monaco Editor, Live Collab, and MCP Server
Wiki.js 3.0 is a complete rewrite with a Monaco editor, real-time collaboration, multi-site support, and ...
Google Open-Sources XLA Serving Engine: Serve JAX Models at 36x Throughput
Google open-sourced XLA Serving Engine (XSE), the C++ inference runtime powering YouTube Shorts and Gemini ...
Inkling 2 Small: 594B MoE Developer Guide (November 2026)
Thinking Machines' Inkling 2 Small scores 86.3% on SWEBench Pro v2 at $1/M tokens. Apache ...
T3 Code 0.1.7: Lock Down Your AI Coding Agent Fleet
T3 Code 0.1.7 ships a managed policy system: deploy one JSON file to lock agent permissions, whitelist providers, and enforce Supervised mode across ...
Tencent Hy4: 770B Vision + Computer-Use Model, Developer Guide
Tencent Hy4 is live on OpenRouter and CodeBuddy. 770B MoE with computer use, 1M context, ...
NVIDIA Cosmos Framework: Post-Train Physical AI in a Day
NVIDIA open-sourced Cosmos Framework with TAO 7 agent skills. Post-train a physical AI world model ...
Mistral Large 4 Weights Are Out: What It Takes to Run Le Chonk
Mistral released the weights for Mistral Large 4 — a 1.05T-parameter open-weight model nicknamed Le ...
gstack: Turn Claude Code Into a Full Engineering Team
gstack gives Claude Code 23 specialist slash commands — CEO, QA, security auditor, and more. ...