L

llm-agents

Open-source computational laboratory for commons dynamics, governance, Seneca cliffs, and generative agents. Four-paper series (BDPD⁰–³) + mini-course + research notes + annotated bibliography on Zenodo. Node.js simulation platform + Python LLM agents + The Forest of Humbaba card game.

A self-improvement flywheel for Claude Code — 4 layers that turn ephemeral sessions into compounding, durable learning.

A series of incremental example usages of promptfoo and its application into LLM related features