Память
Плагины «Память» дают агентам DeepSeek-Harness (dsh) устойчивую память за пределами одного сеанса. Категория включает хранилища долговременной памяти на основе графов, журналы памяти на базе SQLite или Markdown, автоматическую дистилляцию бесед в факты или навыки, а также мосты, импортирующие память из Claude Code или Codex.
Найдено плагинов: 829
dsh-memory-meow
phant0meow/dsh-memory-meow
Память в рамках проекта между сессиями: снимок PROJECT.md внедряется в первое сообщение пользователя, инструмент memory_remember и авто-рефлексия после задач ReAct; у каждого проекта свой файл памяти.
dsh-memory-gate
git121995/dsh-memory-gate
Ограниченная локальная память с контролем полномочий CBDC: утверждения в SQLite + FTS5, целевая выборка с объяснимыми решениями use/verify/ignore и полным журналом аудита, команды /memory, внедрение ≤3 утверждений/1200 символов за вызов, без дополнительных вызовов модели.
dsh-attune
shiyan688/dsh-attune
Generates playful contextual quizzes and uses confirmed, editable preferences in later DSH chats.
dsh-deepmemory
emo-bird/dsh-deepmemory
Cross-session long-term memory for DSH — facts, verbatim episodes and a daily diary in one local SQLite file, plus a sidebar console and per-session switches.
dsh-mini-superagent (dsh-mini-superagent)
wychmod/dsh-mini-superagent
Task dispatch plus a workbench for DeepSeek Harness: the main session hands work to independent background child sessions and returns at once, with each child's report flowing back into the conversation as a message; a Dispatch Workbench in the sidebar shows concurrency slots, queued tasks, batch progress and failure reasons, and each task can be cancelled, retried or archived. Adds 10 dispatch_* tools. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-emotion-memory
xsy822/dsh-emotion-memory
情绪记忆模型 0.1:PAD 情绪场 + 带情感指纹的记忆,一套注入
personal-memory
zhangfac-888/personal-memory
Connects DeepSeek Harness to a locally installed Personal Memory service over HTTP, exposing memory search and retrieval tools.
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.
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.
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.
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.