The TUI and Session manager are straightforward enough. PI is serial by default but can become more DAG-like, where Codex is designed specifically for DAG and this is going more the Codex direction.

I'm much more interested in the memory model and why. As far as I can tell, it's "a vector Db" and not much more is said. Nothing about working memory or procedural memory (there are lots of ways to classify it, https://www.youtube.com/watch?v=BacJ6sEhqMo), but I was disappointed with how "advanced" it seems.

Question: Any benchmarks showing if this actually improves problem solving? Or reduces errors?

"Answer": a word soup that in no way, shape, or form addresses the question, but does sound jargony and vague enough to be an LLM.