I would encourage you to re-evaluate that expectation. A framework comes with strict, mechanical constraints for both developers and agents, while the contents of AGENTS.md can be ignored by agents. Even skills don't always get invoked, and you sometimes have to browbeat your agent to follow a skill or doc. But a framework provides a hard, mechanical guardrail with loud failures and known solutions. Combined with linting, strict types, and a language server, your LLM isn't going to be tempted to invent baffling solutions when a framework provides patterns for long-solved domains.
I would go so far as to argue that all of the reasons that frameworks are useful for human-led projects are equally, if not more applicable to those executed by agents.