Skip to content
NUILab Agentic AI
Concepts Patterns Tools & Frameworks Guides Reference
nuilab.org ↗
Concepts What agentic AI isA multi-machine agent stackSubscriptions, APIs, and local modelsSkills, MCP, and extending an agent
Patterns Tool usePlanningMemoryRetrieval (RAG)EvaluationMulti-agent orchestration
Tools & Frameworks amuxamux-toolshcommosquittoTailscaleClaude CodeopencodeOllama
Guides Set up amux on LinuxRun agents on one machineFind and resume the right conversationConnect machines with hcomLocal and frontier modelsCustomize the Claude Code status lineGive an agent standing instructionsYour first CLAUDE.md
Reference amux cheat sheetClaude Code token & thinking limits

NUILab Agentic AI

Reference

Quick lookups — glossary, APIs, cheat-sheets, and at-a-glance tables.

Reference

amux cheat sheet

Every command you need day to day — amux sessions, the amux-run / amux-attach scripts, tmux keys, and the hcom bus — in one place.

Reference

Claude Code token & thinking limits

The env vars that control thinking budget, output length, and how much tool output enters the context — which models they apply to, when to set them, per-session vs. everywhere, and recommended numbers.

NUILab Agentic AI An open handbook for building agentic AI · maintained in a Git repository Back to top ↑
↑↓ navigate · ↵ open · Esc close