TiramisuCopy MarkdownOpenevolversRecursive self-improvement. Define what you want; an LLM agent iteratively refines the implementation until it meets your criteria.lurkersWeb content for AI agents. HTML, YouTube transcripts, X posts, and RSS — one typed Document model.evolversCompiles your intent and taste into self-improving artifacts. Provide criteria, examples, or both — the LLM iterates toward what you meant.