name: severian repo: https://github.com/Sahil-SS9/Severian sha: bdb14b04ffa014148d4665f239688ca0856561da subdir: "plugins/hermes/severian" version: "0.3.13" description: "Local-first long-term memory for Hermes agents: a canonical append-only store (SQLite or PostgreSQL+pgvector) with five-dimensional tenant/profile/collection/agent/session scope, hybrid BM25+vector retrieval with a re-ranker, memories that cite the observations they came from, per-turn user facts, real dates next to relative times, truth resolution when a newer fact replaces an older one, and a conflict note when two returned memories disagree. Fully offline by default; Qwen3-Embedding-0.6B semantic embeddings opt-in, locally or in a user-owned sidecar. On OmniMemEval's public long-term-memory leaderboard (its own models, prompts and full public sets) it scores 90.6 LongMemEval (1st), 87.3 LoCoMo (2nd) and 71.6 BEAM 100K (2nd, within noise of the lead); it re-ran LCM-X to check the board's records, and per-question results, a strict second marker and scripts are published in the repo. Disclosure — stores every conversation turn in one SQLite database under the Hermes root (`/severian`) shared by all profiles with rows scoped per profile, or in the PostgreSQL database named by `SEVERIAN_DSN`; the opt-in Qwen/Granite embeddings download a model from Hugging Face on first use, and the opt-in embedding sidecar sends memory text to the URL you configure." maintainer: Sahil-SS9 tier: community category: memory docs_url: https://github.com/Sahil-SS9/Severian#readme readme: true platforms: [] capabilities: provides_tools: [] provides_hooks: [] provides_middleware: [] requires_env: - SEVERIAN_DSN