Sources#

Page	Type
Agent Cost Economics: Token Costs and the $5 Trillion Bet	source
Best Memory System for AI Agents in 2026	source
AgentBench: Evaluating LLMs as Agents	source
Agentic AI Governance: Safety, Alignment & Regulatory Landscape	source
The Agentic AI Tipping Point: Non-Code Domains	source
Designing for Agentic AI: UX Patterns for Control, Consent, and Accountability	source
How Hungry is AI? Energy, Water, and Carbon Footprint of LLM Inference	source
strAIght talk: AI Tips for Amazonians (Podcast Notes)	source
Anthropic: Define Success Criteria and Build Evaluations	source
Anthropic Skills Repository & Agent Skills Spec	source
AutoGen: Microsoft’s Multi-Agent Framework	source
BMad Method: AI-Driven Agile Development	source
Claude Code Documentation	source
7 Practical Ways to Reduce Claude Code Token Usage	source
Continuum Memory Architectures for Long-Horizon LLM Agents	source
CrewAI: Role-Based Multi-Agent Orchestration	source
CrewAI in Production — Building Multi-Agent Teams That Actually Deliver	source
Efficient Memory Architectures for Agentic AI Systems	source
How to Evaluate AI Agent Skills Without Relying on Vibes	source
Fabric GitHub Repository	source
GAIA: A Benchmark for General AI Assistants	source
Gas Town	source
Google Agent Development Kit (ADK)	source
HumanEval: Evaluating Large Language Models Trained on Code	source
Interpretable Context Methodology: Folder Structure as Agent Architecture	source
Kiro Autonomous Agent Page	source
Kiro CLI 2.0: Headless Pipelines, Windows, and UX Refresh	source
LangGraph: Stateful Agent Orchestration as Graphs	source
Building Long-Term Memory in AI Agents with LangGraph and Mem0	source
LLM Wiki (Karpathy)	source
My Web Clipper Prompt (LYT)	source
Mem0: AI Memory Management for LLMs and Agents	source
Stop Treating AI Memory Like a Search Problem	source
Microsoft Agent Framework 1.0	source
How to Trace and Debug Multi-Agent Systems	source
Multica	source
Getting The Most Out Of Notes In NotebookLM	source
OpenAI Agents SDK	source
OpenAI Swarm: Lightweight Multi-Agent Orchestration	source
Paperclip: Open-Source Orchestration for Zero-Human Companies	source
Personal AI Infrastructure (PAI)	source
Promptfoo: LLM Evals & Red Teaming	source
Scion Documentation	source
Shared Agent Memory: Stopping Agents from Repeating Work	source
Skills Pipeline (Sleestk)	source
Spec Kit: Spec-Driven Development Toolkit	source
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?	source
Symphony	source
The Ten Pillars of Agentic Skill Design	source
Introducing Trusted Remote Execution (Rex)	source
I’m Going Back to Writing Code by Hand	source