Unofficial TypeSafe Jev showcase — System One decisions, not chat.

Step through GRPO: toy softmax, verifiable rewards, outer-loop agent, optional LoRA GRPO on Qwen2.5-0.5B

The engineering kit for Grok Bot templates. Spec, Bot Ready score, teams, skills, routines, and a catalog you can paste into Grok Bot today.

Fine-tune a small specialist and route every query through NVIDIA NeMo Switchyard.

ClassAct — inspect, run, watch, and build NVIDIA Object-Oriented Agents on Nemotron NIM

Least-data SFT on Qwen2.5-0.5B-Instruct: teach a ticket-card format with 8 examples. Colab T4 notebook + LoRA. Open weights.

What people miss about Grok 4.6 — 200k price cliff, sticky cache, compaction, xhigh, cost lab

Ultimate resource kit for NVIDIA Nemotron 3.5 Lightning + NeMo Switchyard

Introducing Muse Glimmer: open-weight 30B agentic multimodal model that runs on your device (Meta). Interactive local agent lab + guide. Apache 2.0 · on-device AI · function calling

Agentic Supervised Fine-Tuning: SFT on agent traces with LoRA/QLoRA (TRL) on open-weights models — Colab T4 ready

Local macOS meeting assistant — record, WhisperKit live transcripts, calendar, and xAI Ask

Interactive live lab for Grok Voice Think Fast 2.0 — offline demo, reasoning high vs none A/B, speech-to-speech Realtime

Nemotron 3 Embed — NIM semantic search wow demo (nvidia/nemotron-3-embed-1b)

Zero-dependency Python graph runtime for agent loops · Mermaid + ASCII · LangGraph energy, bicycle size

4 viral-grade experiments built on xAI Grok: brutal voice roasts, canonical realtime voice client, voice-driven image gen, and the best X thread generator

What is NVIDIA SpatialClaw? Simple explainer blog + conceptual demo of code as the action interface for spatial reasoning.

Composable harness runtime for production agents — primitives, traces, evolution, outerloop governance.

Own the Outer Loop. Evidence → Verdict → Answerability. Governance layer for agentic engineering.

Markdown memory hygiene for agent wikis, trust decay, context packing, and archive gc

A compounding knowledge base maintained by LLM agents — inspired by Karpathy's LLM Wiki pattern

Runnable illustrations of Assistant (on-behalf-of) vs Claw (fixed-identity) agent authorization

The canonical reference for Grok Build CLI /goal — run-until-done objectives, patterns, verifier skills, and goal-audit CLI.

Long-term memory layer for AI agents

Amazing CLI utilities for Grok Build by Cobus Greyling. 7 power tools: sessions, skills, backup, usage, mcp, worktree, memory.

OpenAI-compatible proxy that routes requests to the best NVIDIA NIM model by task

Practical reference for fleet engineering, governing populations of AI agents with accountability

Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audi…