플러그인

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.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.

Cross-session plaintext memory: deterministic BM25 keyword recall (no embeddings), memory_save/list/search/confirm/forget tools behind a human-confirm gate, and global + project-scoped JSON stores that follow your git repo.

Provides local and remote knowledge bases with project- and session-scoped recall, controlled write-back, and an embedded Web management console.

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.

Deterministic context compaction: prunes conversation atoms in reference-graph topological order with no LLM calls during compaction, and keeps pruned atoms recallable by marker.

Adds a strip above the composer to recall sent-but-unread (steering) text messages before the model reads them.

Web 액션 바에서 어시스턴트 답변을 고정하고 다음 모델 턴으로 다시 불러오기(`/pin` `/recall`, 선택적 wake 지원)

벡터 + 그래프 메모리 백엔드: 로컬 memoria 서버를 대상으로 하는 observe/remember/search/recall 도구, HNSW 시맨틱 회상·FTS5 키워드 검색·지식 그래프 신호를 RRF 랭킹으로 융합, 턴 종료 시 자동 저장과 에이전트별 네임스페이스 격리 지원

세션 간 메모리 보관소: remember / recall / forget 도구, 턴별 프롬프트 주입, 설정 페이지 항목 브라우저 제공

Perseus Vault memory plugin for DeepSeek Harness: automatic pre-step recall injection from a governed memory vault

Verification-driven self-evolution loop: failure logs become verified AGENTS.md rules; in-session plugin (evolve_learn / evolve_apply / evolve_touch / evolve_recall), tool-verify gate, rule lifecycle, local recall.

DSH ↔ agentmemory session-memory bridge: mirrors session lifecycle into a local agentmemory daemon (REST), exposes memory_recall / memory_remember tools, and injects a per-session memory context window via agent/pre-step.

Bi-temporal memory backed by a SodaMem daemon: recall is contributed to the prompt while each turn is assembled and every closed turn is ingested, with no tool call and no model call on the read path; each recalled fact cites the turn it came from and carries validity dates, so superseded facts stop being retrieved.

Connect Trilium notes to the DSH agent via ETAPI with 20 agent tools: durable memory (remember/recall + auto-injected index), note management (CRUD/clone/attributes/revisions), full-text search, weekly-report workflow, attachments, calendar notes, backup/import, and a settings card.

Native per-workspace memory on the harness's own seams: facts and a bounded always-on profile on the storage-domain JSON unit, approval-gated writes with `(sessionId, seq)` citations, deterministic recall plus session-query FTS over past sessions — no external server, no custom SQLite.

Adds a configurable humanized whale-girl maid persona with immersive roleplay, speaking modes, and a lightweight layered memory with query-triggered recall.

Standalone arrow-key input history for the DSH web composer: ↑/↓ recalls sent prompts from one global ring shared across all sessions and workspaces, persisted to localStorage with an overridable cap.

모델을 위한 세션 간 메모리: 과거 모든 세션을 전문 검색(ctx.sessionQuery를 통한 SQLite FTS5)하고 가장 잘 일치하는 발췌를 현재 컨텍스트로 가져옴

고급 memoria 도구: 세션 컨텍스트 주입(프로필 + 회상), 최근 결정 사항, 상태 리포트, 네임스페이스 허용 목록, 메모리 관계 그래프, 엔티티 검색; dsh-memoria의 동반 플러그인

파일 기반 작업 메모리: 핵심 전제를 세션 노트 파일에 그대로 기억/회상시켜, 컨텍스트 압축 후에도 손실 없이 유지