메모리
메모리 플러그인은 DeepSeek-Harness(dsh) 에이전트에게 단일 세션을 넘어서는 지속적인 기억력을 부여합니다. 이 카테고리는 그래프 기반 장기 메모리 저장소, SQLite 또는 Markdown 기반 메모리 로그, 대화를 사실이나 스킬로 자동 압축하는 기능, Claude Code나 Codex에서 메모리를 가져오는 브리지를 다룹니다.
플러그인 817개 찾음
dsh-memweave
lw24-1936/dsh-memweave
Memweave is a DSH organizational memory and task-evolution plugin. It decomposes goals into task networks, captures verifiable judgments and anti-patterns, and tracks iteration with measurable Loops. Features visual storage settings, category browsing, lifecycle management, and data exchange with existing plugins.
dsh-knowledge
avenyq/dsh-knowledge
Sidebar knowledge base for DSH: indexes local Obsidian vaults and project folders into SQLite FTS5, re-indexes file changes automatically, shows source snippets while you type, and lets the agent answer with numbered citations that open the exact source file and line. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-plugins-cooper-custom
cooperzhuang/dsh-plugins-cooper-custom
Cross-session memory for the DeepSeek Harness: project-scoped and global memories with an explicit memory tool, idle-time background extraction, consolidation, and layered summary injection
eventmem (dsh)
wackyju2-beep/eventmem
Local-first event memory for DSH: recall injection, seven memory tools and a native console. Install the eventmem daemon separately; SSH sharing is opt-in and no private host is a default.
dsh-seed-of-memory
ruiyuanyisu/dsh-seed-of-memory
Local-first memory for DSH — identity root, layered memories, beliefs, an emotion kernel and QQ chat continuity, all in one SQLite file. The QQ chat bridge replies only to the QQ numbers and groups on its allow-list, which is empty by default, so it answers nobody until you fill it in.
meow-starmap
hirschno/meow-starmap
Star map of the meow-memory store: each memory a glowing star, project memories gathered around a galaxy core, edges from project membership and shared keywords, fading into galaxies when zoomed out. Read-only.
dsh-recollection
cqxsg/dsh-recollection
Lets DeepSeek Harness agents autonomously search and revisit original history from the current session that has been removed from the model's context by compaction. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
agent-skill
velestia-star/agent-skill
Build named subagents and skills in a sidebar panel, then call any subagent by name in a conversation. Each subagent selects a model, reasoning effort, spawn or fork mode, a tool allowlist and skills; skills can be global, per workspace or per conversation.
dsh-cortex-memory
lh1314-china/dsh-cortex-memory
A layered, temporal, self-developing memory engine for DeepSeek Harness
dsh-compact-arsenal
tacitsay/dsh-compact-arsenal
Configurable context compaction with three independently switchable sections — whole-context checkpoint, reasoning compression and tool-output pruning — each with its own pressure threshold and method. Mechanical modes make no model calls; model modes summarize fragments in batches with a configurable provider and prompt. A left-sidebar panel exposes switches, method cards and editable parameters that save without a restart, and every rewrite is archived with its original text.
dsh-memory
rosesssss66/dsh-memory
Local long-term memory for DSH: extracts preferences and project facts from sessions, injects the most relevant ones before each turn using local SQLite FTS5 search, and supersedes outdated facts. Requires Node 24+; the offline self-evolution loop needs an OpenAI-compatible LLM endpoint and API key.
dsh-memories
libraqg/dsh-memories
Long-term memory ported from the OpenAI Codex memory pipeline: sessions idle for 6 hours are extracted in the background by a chosen model, then merged by a hidden agent into a Markdown memory folder at most every 6 hours; new agents get the memory summary in the system prompt plus four tools to list, read and search memory and save corrections. Models are chosen on a settings page or with /memories; an optional filter keeps a notes folder out of memory.
dsh-membubble
burninice/dsh-membubble
Bounded-context memory for long-running dsh conversations and large group chats, with a focus-limited person pipeline, a fixed injection budget, and append-only event archives.
milancat-bot
alexbu512/milancat-bot
Grok-bot-style AI organization in the sidebar: a chief-of-staff agent creates departments, roles and per-department group chats, dispatches each task to child agents running on this machine, and reports finished work back as one assistant message. Its HTTP routes have no DSH access check, and they can create agents and dispatch tasks to them.
dsh-lessons
duahcim/dsh-lessons
Records task boundaries and structured reflections, stores reusable lessons, and injects them into later tasks according to scope.
almost-for-ever
zwebzzz/almost-for-ever
Derives the index from your Markdown memory files on every turn instead of keeping a hand-written index table, so renames, splits and deletions never leave a stale entry. Retrieval ranks by library tags, section tags, title tokens and body text, then injects the matching line ranges rather than whole files. Writing is model-proposed and user-confirmed through a sticky note; entries are appended after the target section's format is detected. Ships a structure panel showing each library and section with line ranges and token estimates, a starter template for an empty memory directory, and optional appearance controls.
dsh-persona-memory
paanggaasam/dsh-persona-memory
Daily session digest that grows a user profile and a companion personality, gated by evidence, and injects both into every prompt. Runs daily at 17:00 by default over up to 20 sessions per run on the host model (deepseek-v4-pro), applies the results automatically, and injects up to 1200 characters of profile and persona into every prompt. Its package name, dsh-persona-memory, is also used by other listed entries, so install only one of them.
mirror-dsh-adapter
gjhhjfgh/mirror-dsh-adapter
Local-first memory governance: distills conversations into categorized memories, surfaces conflicts for human arbitration, and previews what gets injected next turn.
alice-memory-llm
cycocyco/alice-memory-llm
Long-term memory for DSH where an LLM decides what to keep: turns pool while the session is idle, then the main chat model distills them into one-line entries in a single batched call; vector dedup runs before insert, so near-duplicates and saturated topics are dropped; recall uses hybrid vector plus FTS5 search over tiered hot, warm and cold storage; ships remember, recall, forget and prune tools. Zero dependencies, Node only.
alice-memory
cycocyco/alice-memory
Long-term memory for DSH: rule gates capture durable facts from conversation turns into a single SQLite database with tiered hot, warm and cold storage; recall injects hybrid vector plus FTS5 hits into the prompt each turn; ships remember, recall, forget and cold-memory prune tools. Zero dependencies, Node only.
dsh-hand-note
amd47802574/dsh-hand-note
Local jot-down notes for DSH: one Markdown file per note, stored under ~/dsh随手笔记 by default (portable home path, no drive-letter assumption). Redesigned card UI, trash bin (deletions restorable for 30 days), custom tag management with stable per-tag colors (create tags ahead of use, delete one everywhere), compact/comfortable density, adjustable font size and line width, flat quick-scan list, full-text search, Markdown preview, autosave, batch deletion, zero-dependency Office text extraction, and AI write-back from conversations. Heavily reworked from dsh-knowledge-lite; pick the old library via the in-app root picker to migrate.
dsh-ladder-superagents
yukikaze-ai/dsh-ladder-superagents
Ranks models in a ten-slot ladder, routes each subagent by a 1-10 difficulty, and falls back a tier when one fails. Windows only; applies to sessions that opt in. Subagents can also launch local agent CLIs (Codex verified, nine others experimental), and a subagent granted full authority runs its CLI with --dangerously-skip-permissions, --yolo or --force. Run records go to .dsh-supa/ in the workspace.
dsh-spirit
drscrewdriver/dsh-spirit
DSH 第一人称体验与本体记忆插件:把流程事件编译成角色的体验点滴,并从交付/实体/任务线维度建立可回查的工作记忆(SQLite),在模型步骤前注入「此刻状态 + 刚发生的 + 被勾起的回忆 + 正在推进的事」。
dsh-recovery-memory
zilta-amaze/dsh-recovery-memory
Conversation memory behind a 20-letter recovery code: /recovery create packs the current conversation into one local record, and /recovery memory <code> injects it into a new conversation, where the model first summarises the recovered session and ends its reply with 记忆已恢复. Records are plain JSON under $DSH_HOME/recovery (mode 0600) with no network calls; the restored transcript is complete unless it exceeds the configured character budget, and /recovery where plus the dir option or DSH_RECOVERY_DIR move the directory to shared storage or a synced folder.