Find the right DSH plugin
for your next workflow

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.

Cross-session event-cue memory for DeepSeek Harness: auto-extracts task/conversation cues and user language habits from every turn into a persistent global cue bank, then re-injects remembered context on topic-switch detection (keyword or vector matching).

Karpathy LLM Wiki pattern knowledge base for DSH: wiki-write/wiki-search skills, zero-dependency pipeline (lint/index/mnemon memory sync/quality feedback), minimal lifecycle plugin injecting schema + knowledge preview, SiliconFlow semantic recall via an Ollama-compatible proxy.

Hindsight long-term memory for DeepSeek Harness: injects relevant memories before each turn and retains finished turns to a Hindsight bank.

Cited memory over DSH's lossless session log: distilled facts carry `(sessionId, eventRange)` citations that expand back to the exact original log excerpt.

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with automatic turn-end persistence and per-agent namespace isolation.

Advanced memoria tools: session context injection (profile + recall), recent decisions, health report, namespace allowlist, memory relation graph, and entity search; companion to dsh-memoria.

BM25 keyword-based memory recall.

Dual-ledger cross-session memory: auto-extracts lasting facts from conversations into MEMORY.md and maintains a PROGRESS.md project ledger, recalling both into every new session.

Session context triage for long DeepSeek Harness sessions: deterministic screeners trim stale, duplicate, failed, and oversized content through the official ctx.compaction seam.

Memory Standard Protocol (mm) for DeepSeek Harness: layered MEMORY.md with hard budgets, frozen snapshots, mm:// URI interop, session-log digestion, mem_* tools and a standalone CLI.

Long-term memory for DSH: conversations auto-distilled into atomic facts, scene summaries and a persona profile, with relevant memories injected before every model step. Zero-config out of the box — hybrid BM25 + vector retrieval, optional offline local embeddings, chat/work family separation.

Cross-session long-term memory: dual-scope user/project SQLite stores, FTS5 + offline local vector hybrid retrieval, 9 engram_* tools, per-turn automatic capture, a distillation flywheel, provenance audit, and a bilingual Settings memory-library panel.

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.

Organize folders and sessions into projects with shared PROJECT.md memory and AGENTS.md instructions injected into every session, plus a project tree sidebar.

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

Project-level Local Context Engine for DeepSeek Harness: retrieval/compression/prioritization over history, code, files, user preferences and agent trajectories, producing a dynamic context window for any LLM.

Workspace-isolated durable memory for DSH, with searchable, auditable, correctable, and removable workspace memories plus controlled global memory.

Fully local vector memory for DSH: local embeddings, SQLite storage, automatic recall injection, dedup with conflict detection, soft-delete recycle bin, online backup, and optional LLM extraction.

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, hard-injected at every session start, plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice.

Compaction backend replacing LLM summarization with a deterministic semantic extractor (keeps code/paths/commands, drops chatter) plus 28.4x KV-compression accounting.

LLM-driven remember/forget memory: after each turn a model decides what to keep (MemoryDirector), injects relevant memories before each step, dedups, and persists cross-session.

Automatic conversation distillation: background subagent reflection + skill create/update.

Human-readable Markdown memory for DeepSeek Harness: user-level (~/.deepseek-harness/MEMORY.md) + workspace-level memory injected every turn, auto daily-log writing with distillation, bridges existing WorkBuddy/CodeBuddy memory dirs, memory_note / memory_note_user / memory_read tools with built-in dedup, and a bilingual settings page. Plain-text storage, no database.