Software
Software repositories are living systems. Commits, reviews, comments, releases and failed tests show how work moves, where it stalls and what is likely to happen next.
A world model can ask:
- Which pull requests will merge, and when?
- Whose turn is it?
- Where is work drifting from the way this repository normally operates?
- Which events or contributors look unusual?
- How does the forecast change if a pull request is split or reviewed now?
Current work: Project OSS
Project OSS learnt from 7.04 million events across Rust, Kubernetes, Node.js, Nixpkgs, Airflow, Bitcoin, Ghost and OpenCV. It then worked zero-shot on OpenClaw, a ninth repository it had never seen.
On OpenClaw it reached 0.859 AUC on 28-day merge and 0.711 rank correlation on time to merge without retraining. The same model predicts review rounds, next actor, contributor churn and unusual pull-request behaviour.
See the scored results · Open the detailed report — review access
Current work: World Router
World Router applies the same idea to AI work. It follows a task as it moves through prompts, tools, tests, workers and results, then chooses what kind of model or council should act next.
Across 386 recorded worker runs from Rohit's Codex history, it cut estimated model spend by 37% against assigning every run to Sol High and by 62% against Sol Extra High.
See how World Router works · See the comparison
Where this goes
The larger goal is not another repository dashboard. It is an agent that understands the software world it is responsible for: what matters, what is stuck, what changed, what should happen next, and whether its last action helped.