Memex8
Self-hosted vector memory (Qdrant + TurboQuant compression) with auto-discovered knowledge realms, semantic search across conversations and ingested documents, and a slumber pipeline for memory consolidation. v1.1.0 adds optional per-session injection dedup with char-budget gate, decision/evaluation memory-type promotion (slower decay for load-bearing turns), prompt-injection sanitization on read, configurable system-prompt template, export/import memories as JSON, and a /memex8 slash command. New memory behaviours are opt-in; /memex8 export|import is confined to $HERMES_HOME/plugin-data/memex8 unless enable_export_import=true.
Good to know before installing
Auto-stores a truncated copy (first 300 chars) of every user and assistant turn, plus per-message previews of the whole transcript at session end and before context compression, to the memex8 server at MEMEX8_BASE_URL (self-hosted; default http://localhost:8080) using MEMEX8_API_KEY.
From the plugin's catalog listing.
How to install
- Install it. Hermes asks for any API keys it needs (this one needs
MEMEX8_API_KEY), then asks whether to turn it on.hermes plugins install memex8 - Said no? Turn it on later:
hermes plugins enable memex8 - Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide (opens in a new tab).
- Category
- Memory & notes
- Maintained by
- Ex8-ca (Community)
- Needs
MEMEX8_API_KEYAPI key- Needs Hermes
- 0.21.4 or newer
- Version
- 1.1.0
- In the catalog
- 2026-09-27, updated 2026-10-02
- GitHub stars
- 17
Full setup & settings ↗Source code ↗
More in memory & notes
New Hermes Agent updates every day on X. Follow @HermesWatcher