Neural Forge keeps the public open-source story focused on the memory layer: private agent silos, shared hive state, and curated lessons that survive past a single chat.
Memory Hive is the repo users should inspect, install, and contribute to. Other internal Hive-related systems stay out of this public GitHub index.
Persistent memory for AI agent teams.
Private agent silos plus a curated shared hive, so sessions resume with less re-explaining and less context-window waste.
This repo documents reusable patterns without exposing private tokens, hostnames, runtime logs, or machine-specific control details.
Owner consent and clear machine boundaries come first.
Live canaries beat stale memory or theoretical configuration.
Transport success is not execution success until output proves it.
The public repo uses placeholders and patterns, never private runtime details.