Plugins

Curated file-based long-term memory for DeepSeek Harness — human-readable markdown notes, one plain-file store shared across hosts (git-ignored when it lives inside a project repo), and a deterministic index cap enforced by ctx.tools.guard()

The Engramory curated-memory discipline as an installable plugin ([npm: dsh-engramory](https://www.npmjs.com/package/dsh-engramory)): a deterministic 200-line / 25 KB cap on the `MEMORY.md` index via `ctx.tools.guard()` — growth denied, a shrinking rewrite always passes — plus the protocol registered as a runtime skill. The store is plain markdown, one file per fact, shared with Claude Code, Codex, Kiro, and OpenClaw.

Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.

Intégration approfondie de Mnemon : mémoire locale à trois niveaux (Runtime Memory, Documents consultables, Memory Spaces supervisés).

Mémoire inter-sessions : SQLite avec un miroir Markdown éditable par un humain, consolidation en arrière-plan (déduplication, fusion, résolution de conflits), et six outils de mémoire.

Technical-preview local graph memory for DSH and Codex: recalls owner-global and current-project evidence before each turn, writes USER and ASSISTANT records separately, and preserves project, session, actor, and source provenance for a visual atlas and cited knowledge pages.

Long-term memory & self-evolving plugin for DSH: L0 capture → L1 memory extraction → L2 scene grouping → L3 user persona, auto recall injection, skill synthesis, fully local (SQLite FTS5 + jieba, optional vector recall).

File-based cross-session memory: plain Markdown memory files with automatic retrieval injection, format-compatible with Claude Code's CLAUDE.md and memory files, so migrating is a manual file copy.

Mémoire locale bornée avec contrôle d'autorité CBDC : affirmations SQLite + FTS5, rappel ciblé avec des décisions explicables d'usage/vérification/ignorance et une piste d'audit complète, commandes /memory, ≤3 affirmations/1200 caractères injectés par appel, aucun appel modèle supplémentaire.

Biomimetic memory system for DeepSeek Harness: plain-Markdown data layer, memory tools, frozen-snapshot injection, graded approval gating, structured audits, memory metabolism (dream), memory pins, semantic recall, /memory command, and cross-session retrieval.

Faithful port of the hermes-agent MEMORY.md / USER.md mechanism for DSH: bounded dual-bank memory (2200/1375 chars), a single `memory` tool (add/replace/remove/batch), frozen-snapshot injection per session, nudge reminders, DSH-native JSON storage — zero external dependencies, zero LLM cost.

Système de mémoire à long terme structurée pour DeepSeek Harness -- paires résumé/complet par unité avec injection automatique.

Native StrataGate layered long-term memory for DeepSeek Harness

Long-term memory injected at session start: preferences/facts/summaries/knowledge in global and per-project scopes, budgeted recall via `agent/pre-step`, durable JSON store.

Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.

Automatic, local-first cross-session memory for DeepSeek Harness: layered Event/Element cards, evidence-gated recall, and expansion back to original turns and tool results.

Mémoire de persona persistante à long terme pour DeepSeek Harness : stockage MEMORY.md/USER.md, outils memory + memory_search, injection de contexte par requête, et détection de secrets. Portage dans l'esprit de pi-hermes-memory.