This is your work, valued
I explore AI agents, harness & loop engineering. Author of loop-engineering (9.5k★). cobusgreyling.com
LlamaIndex. LlamaIndex Notebooks
31NVIDIA-Nemotron-3-Super. Controllable reasoning demos for NVIDIA Nemotron 3 Super (120B/12B MoE) — chat UI, CLI, API server, tool calling, budget sweep, and adaptive routing
29claude-agent-teams. Claude Code Agent Teams — Multi-agent orchestration from your terminal (Opus 4.6)
12ai_harness_engineering. Minimal Agent Harness — Six harness components demonstrated with NVIDIA Nemotron 3 Super
6hugging-face. HuggingFace notebooks
3claude-agent-sdk-blog. Building Specialised AI Agents with the Claude Agent SDK — blog and 8 demo agents
3nemotron-terminal-blog. NVIDIA Nemotron-Terminal — The CLI Is The Path To AI Autonomy
3claude-agent-approaches. Three approaches to building AI Agents with Claude — SDK, Markdown, and Teams
3langgraph-example. Python
2cli-path-to-autonomy. Blog: The CLI Is The Path To AI Autonomy — connecting NVIDIA terminal study, Steinberger's CLI-over-MCP position, and Anthropic's Vercept acquisition
2gaze-safety-monitor. Real-time gaze safety monitor demo for human-in-the-loop agent oversight
2right-sizing-ai-agents. Right-Sizing AI Agents: Why Specialization Beats Scale — Blog, code examples, and architecture diagrams exploring NVIDIA Nemotron 3 specialized model stack for production agentic AI
2OpenAI. OpenAI API notebooks and early experiments (legacy; archived)
1DialogFlowWeatherBot. Example Bot Showing the weather with basic filfullment
1replace-mcp-with-cli. Replace MCP with CLI — why the command line may be the best AI agent interface
1nvidia-riva-voice-agent. NVIDIA Riva voice agent — ASR + LLM + TTS with Gradio web UI
1agent-audit-tool. AI Agent Safety & Governance Auditor — Intent Laundering, Instruction Fade-Out, Policy Testing, OWASP Agentic Top 10, Compliance Reports
1llm-in-sandbox-dashboard. LLM-in-Sandbox with Agent Observation & Monitoring Dashboard
1ai-agent-benchmark. AI Agent Benchmark Suite — 5 real-world coding tasks to benchmark any AI coding agent. One suite. Every agent. Real scores.
1claude-code-hooks. Claude Code Hooks: Deterministic Control Over Non-Deterministic AI — blog, demo code, and diagrams
1hyperagent-harness. Self-improving agent loop demonstrating emergent harness components — HyperAgents meets Harness Engineering
1nvidia-aiq-agent. NeMo AgentIQ — Enterprise Agentic RAG with Multi-Source Reasoning. Powered by NVIDIA NIM & LangChain/LangGraph.
1nemotron-multi-doc-reasoning. Comparative document analysis with transparent chain-of-thought using NVIDIA Nemotron Super 49B
1ai-agents-less-context. AI Agents Are Better at Building From Scratch With Less Context — Minimal prompts outperform detailed prompts for code generation
1FlowPilot. AI-Powered Workflow Automation - Describe workflows in plain English, FlowPilot wires up the APIs automatically.
1nim-explorer. Gradio app for browsing, chatting with, and comparing NVIDIA NIM models
1token-hidden-compute-primitive. The Token is Becoming the New Hidden Compute Primitive — Tokens are following the same path as CPU clock cycles, from headline metric to invisible infrastructure
1