CortexLayer memory provider — page-linked long-term memory with link-expansion retrieval, wired into Hermes' automatic per-turn recall (prefetch) and persistence (sync_turn), plus a pre-compress checkpoint so evidence Hermes' own context compaction would otherwise drop is saved first. Platform mode only: each turn's query and conversational content is sent to the hosted api.cortexlayer.net (HTTPS, API-key authenticated) for storage/retrieval — no local/offline mode. Requires a free CortexLayer account and API key.
hermes plugins install cortexlayeron_session_endon_pre_compressCORTEX_API_KEY099e4b3 ↗; it updates when the author re-pins.CortexLayer memory, wired into Hermes' automatic per-turn prefetch/sync. See the
repo README for install, configuration (default_user_id), and the
design decisions this implementation follows (task 0088).