Self-Improving Agents -- A Progression Four levels of self-improving code agents, from the simplest loop to a full adversarial arena with self-modifying agents. Each level adds one key idea.
1 file for Claude Code: self-improving-agents CLAUDE.md — 1,702 tokens loaded in every session.
CLAUDE.md A 1,702 tok These files are BetterForAll/self-improving-agents's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.