Practical AI · Thursday, July 9, 2026
Hamza Tahir identifies a key industry tension between proprietary AI agent frameworks, like Claude Code, which are tightly coupled with specific models, and open frameworks like LangGraph or Pythontic AI. The latter aim for open standards, seeking to avoid vendor lock-in and reduce dependency on specific model providers.
“Now, on the same time, there has been a renaissance of open harnesses, right? So we have Pi, we have frameworks like LangGraph or Pythontic AI.”
“And those harnesses are of the opposite opinion, that they should have an open standard, that shouldn't be tied to the model, because we don't want the user's, you know, the US government decides to ban and unban models, that shouldn't affect our business outcomes.”
“And, and that has been an underlying tension in the industry for the last year, um, and hasn't resolved yet.”