Public controller, memory, reward and self-improvement core for Openclaw intelligence upgrades
| configs | ||
| docs | ||
| scripts | ||
| syncpatch | ||
| README.md | ||
Openclaw Intelligence Core
This repository tracks the new intelligence-controller slice for Openclaw:
- typed trajectories
- reward signals
- replay buffer / policy stats
- typed tool graph
- uncertainty model
- shadow meta-controller
It is intentionally narrow: this repo is the source-of-truth for the new learning and controller layer, not the entire legacy Openclaw workspace.