Roadmap

Zorp is pre-alpha. The execution harness and the research foundation are built and tested, as are all four capabilities: validate, investigate, co-write, and deliver. It is not yet a finished product, and this page will not pretend otherwise.

Shipped

• [x]Base execution harness
• [x]Research foundation: tracks, evidence records, pre-registration, checkpoints
• [x]validate
• [x]investigate
• [x]co-write
• [x]deliver
• [x]Developer mode: local pretraining, and serving a trained checkpoint in Zorp

Not yet

• [ ]A published investigation trace, start to finish
• [ ]A grounded-vs-baseline evaluation
• [ ]A systems paper about zorp itself, submitted to arXiv
• [ ]Zorp RL: fine-tuning an existing open model on your own data
• [ ]Zorp RL: turning local usage logs into training data
• [ ]Zorp RL: automated retraining that keeps a model only when it measures better

This list moves as the work does. Follow it in therepository, where it's kept in sync with the README.