Categories › Conversation & context
Conversation & context
1005 pluginsSession management, long-term memory and context compression — longer, more coherent, remembering conversations.
Sorted by downloads. 100 per page.
"https://github.com/Missher12/Missher-MSE-Learning/releases/download/v0.9.0-alpha.18/missher-dsh-mse-learning-0.9.0-alpha.18.tgz"
Persists scoped user corrections and method candidates for DSH with bounded recall and res
↓ 0
"https://github.com/QqiqiQ/dsh-profile-vault/releases/latest/download/dsh-profile-vault.tgz"
A consent-gated personal profile store: people are indexed by name, entries by person and
↓ 0
"https://github.com/reshuibuduo/tmcra-plugin-deepseek-harness/releases/download/v1.0.0-rc.1/dsh-tmcra-memory-1.0.0-rc.1.tgz"
Cross-app project memory for DeepSeek Harness with role-separated writeback, a visual know
↓ 0
"https://github.com/Root-7-KHX/companion-memory/releases/download/v1.2.2/local-companion-memory-1.2.2.tgz"
Roleplay companion memory for DeepSeek Harness: per-conversation editable persona document
↓ 0
"https://github.com/shadowRjh/dsh-neuron-memory/releases/download/v2.7.0/dsh-neuron-memory-2.7.0.tgz"
Neuron-inspired memory for dsh: turns buffer into a hippocampus, a nightly patrol classifi
↓ 0
"https://github.com/shua-781/dsh-beme/releases/download/v0.1.5/dsh-beme-0.1.5.tgz"
Long-term memory kept as blocks: one event per block, written to a local append-only event
↓ 0
"https://github.com/sxwer001/dsh-context-control/releases/download/v0.1.3/dsh-context-control-0.1.3.tgz"
A context usage ring with configurable character-based automatic compaction, manual compac
↓ 0
"https://github.com/tabilet/tabilet-skills/releases/download/v2.16.2/tabilet-skills-2.16.2.tgz"
Seven shared engineering skills, a read-only project dashboard with amendments, options, s
↓ 0
"https://github.com/vv5v5/dsh-memory-archive/releases/latest/download/dsh-memory-archive.tgz"
RP memory built on pmp tavern: RP history summaries ride the native compaction pipeline, w
↓ 0
"https://github.com/WsTe47/mylife/releases/latest/download/mylife.tgz"
A local-first personal state record and decision engine for dsh: keeps every input byte-fo
↓ 0
"https://github.com/xingyueDanYang/dsh-puppet-memory/releases/latest/download/dsh-puppet-memory.tgz"
Cross-session memory for DeepSeek Harness: a three-tier store (behavior notes, deep detail
↓ 0
"https://github.com/xying-lm/dsh-memory-vault/releases/latest/download/dsh-memory-vault.tgz"
Disk-backed long-term memory for DSH: a SQLite FTS5 vault that captures every conversation
↓ 0
"https://github.com/Yang-Yin734/dsh-long-term-memory/releases/latest/download/dsh-long-term-memory.tgz"
Adds a long-term memory box to the DSH Settings page. The saved text is injected into the
↓ 0
"https://github.com/yangyizhu8/dsh-powercontext/releases/download/v0.0.3/powercontext-dsh-0.0.3.tgz"
PowerContext for DeepSeek Harness: WorkBuddy-style project memory and inspectable handoff
↓ 0
"https://github.com/yihefeikong-rgb/dsh-cc-haha-dream/releases/download/v0.1.0/dsh-dream-0.1.0.tgz"
Background memory consolidation (auto dream) for DeepSeek Harness: periodically reviews re
↓ 0
"https://github.com/yihefeikong-rgb/dsh-cc-haha-memory/releases/download/v0.1.0/dsh-memory-0.1.0.tgz"
Persistent memory for DeepSeek Harness: memory read/write/retrieve tools, per-turn auto-re
↓ 0
"https://github.com/yunkong-134/xiaoman-memory/releases/download/v0.2.0/xiaoman-memory-0.2.0.tgz"
Plain-text memory for DSH where every event is one Markdown section with six fields, recal
↓ 0
"https://github.com/yxie15022-debug/dsh-wife-memory/releases/download/v0.4.1/dsh-wife-memory-0.4.1.tgz"
Long-term memory about the owner: extracts schedule, likes, dislikes, emotional triggers,
↓ 0
github:LornBerry/dsh-memory-center
Local long-term memory for DSH: browse, search (BM25 + synonyms) and edit entries in a pan
↓ 0
github:LoserFox/distill
Automatic conversation distillation: background subagent reflection + skill create/update.
↓ 0
github:luxiwusuobuneng/dsh-plugin-context-manager
Context manager for DeepSeek Harness: auto-summarizes every turn into priority-sorted reco
↓ 0
github:lzk112233/dsh-self-memory
Four-layer memory for DeepSeek Harness, ported from the memory design of NoMindSama/qq-dsh
↓ 0
github:madage/dsh-self-improved
Long-term memory & self-evolving plugin for DSH: L0 capture → L1 memory extraction → L2 sc
↓ 0
github:menotbobbybrown/dsh-plugin-memory
Persistent long-term memory for DeepSeek Harness: a JSON store of typed entries (fact, pre
↓ 0
github:mess1103/dsh-inner-life
A private diary for your agent: eight zero-dependency tools to write, amend, search and ex
↓ 0
github:MiHjy12138/dsh-memory-lite
On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a
↓ 0
github:MingHuanYue/dsh-iter-memory
Iter Memory: it remembers my own state, not the facts. A level that drifts back to baselin
↓ 0
github:MingHuanYue/dsh-tide-memory
Tide Memory: a long-term memory that forgets on purpose. It keeps what matters and lets th
↓ 0
github:MingoYung/dsh-Xiangxu-Persona
Persistent persona memory for DSH with a unified recent, long-term and archive timeline, b
↓ 0
github:moondrop12138/dsh-zcode-workspace-memory
Workspace memory for DeepSeek Harness ported from ZCode: one Markdown memory directory per
↓ 0
github:moononnn/DeepSeek-Harness-Hanako-Memory
Hana-style assistant manager for DSH: visual preset management (cards, yuan personalities,
↓ 0
github:NEVSTOP-LAB/dsh-import-copilot-files
Loads a workspace's VSCode/Copilot AI configuration into every DSH session: `.github/copil
↓ 0
github:nineoooo/dsh-qzone-echo
Archives the QQ Zone posts you published yourself into a local library, auto-sorted into t
↓ 0
github:nowledge-co/nowledge-mem-deepseek-harness
One memory layer for every AI tool and agent: Context Bundle injection, prompt-time recall
↓ 0
github:NoxTyrannus/dsh-cipher
Cipher memory platform as a DSH bundle: four memory types (attention, experience, preferen
↓ 0
github:omdsh-dev/dsh-kb-sieve
Build auditable KB packs (SQLite FTS5) from md/txt/docx/pdf with deterministic retrieval a
↓ 0
github:orangeshinee/dsh-mem0
Agent tools for a self-hosted mem0 server: add, search, get, update, delete, history, rese
↓ 0
"https://github.com/qibo30/dsh-worklog/releases/latest/download/dsh-worklog.tgz"
Cross-session development worklog for the agent: worklog_add appends one line (optional ta
↓ 0
github:plur-ai/dsh-plugin
PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool
↓ 0
github:pokiimon/dsh-memory-eternal-fork
Maintained fork of dsh-memory-eternal: auto-captures knowledge cards into a local Markdown
↓ 0
"https://github.com/QIANLING-0831/dsh-memory-plus/releases/download/v0.2.2/dsh-memory-bundle-0.2.2.tgz"
Memory profile composition with Chinese session search, hybrid recall, persistent workspac
↓ 0
github:QuantumKuba/dsh-continuum
Persistent project memory, event-sourced task lifecycle, context budgeting, and cooperativ
↓ 0
github:qwert702/dsh-memory
Project+global long-term memory for the dsh web GUI: split POST /items endpoints, tool-cal
↓ 0
github:reatcat/l123-harness
Three-tier agent memory harness: L1 always-on CLAUDE.md, L2 index, L3 detail skeleton with
↓ 0
github:rebron1900/dsh-mnemosyne
Mnemosyne memory for DeepSeek Harness: remember / recall / forget / stats / sleep tools, e
↓ 0
github:RocoFish/deepseek-memory
Long-term memory for dsh with defense-in-depth hardening. Two tiers (project `.dsh-memory/
↓ 0
github:Rxiain/dsh-openviking
Semantic retrieval, resource management, auto-recall (user + agent dual spaces) and sessio
↓ 0
github:scd13150/dsh-cognition
Project memory for coding agents on DeepSeek Harness: similar past edits surface as preced
↓ 0
github:SeanWang114514/dsh-memo-notebook
Per-workspace memo/todo panel that auto-captures queued and running user instructions, mar
↓ 0
github:SiriusWJ/dsh-lite-memory
SQLite memory entries, a calendar with due-time reminders, and cron-scheduled agent tasks,
↓ 0
github:SMPcosy/dsh-memnexus
Unified long-term memory hub: captures turns into L0 evidence, distills in the background
↓ 0
github:snakejohn/dsh-hindsight-local
Long-term memory for dsh via a local Hindsight service: each turn is retained with local t
↓ 0
github:Snerou/dsh-hippo
Hippocampus: renders workspace files, DSH memories and past sessions as a rotatable neuron
↓ 0
github:SQHLnb666/mindsea
A long-term memory plugin for DeepSeek Harness. Every turn is judged and stored into a loc
↓ 0
github:suomir1995/dsh-notes
Keeps notes as local Markdown files grouped by directory under a root folder you choose, w
↓ 0
github:Swd146296/dsh-memos-bridge
Bridges the MemOS memory service over MCP: the agent gets add/search/update/delete memory,
↓ 0
github:swenbo1-web/agents-learning
Project-scoped SQLite memory with progressive retrieval, bounded context, a composer butto
↓ 0
github:Tangcuyu4/dsh-long-memory
Cross-session long-term memory: a hybrid-retrieval memory store (BM25 plus CJK bigrams), c
↓ 0
github:thawline/dsh-memewiki
Offline meme and slang dictionary: 6,668 built-in entries are looked up before a turn and
↓ 0
github:Toctsu/dsh-full-life-memory
A biomimetic memory plugin for DSH that folds context into token clues and reconstructs me
↓ 0
github:TodayJin/dsh-trilogy
Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md,
↓ 0
github:Tommy00748/dsh-self-evolution
Bounded self-managed long-term memory (Hermes-style MEMORY.md / USER.md with hard characte
↓ 0
github:tynr426/dsh-relationship
Local relationship-memory workbench with a confirmation gate: every AI write — extracted m
↓ 0
"https://github.com/vv5v5/dsh-anima-rag/releases/latest/download/dsh-anima-rag.tgz"
Anima-style vector memory for DSH: injects retrieved historical summaries into the system
↓ 0
github:wafernm-crypto/dsh-memory-library
Per-workspace memory library with manual per-chat opt-in, editable rules, three sharing mo
↓ 0
github:weirwei/dsh-logseq
Syncs Logseq 2.0 DB graphs (including E2EE) with a Logseq sync server via the headless Log
↓ 0
github:whding110/dsh-dev-progress-memory
Per-turn development progress memory: completed turns are classified into date-indexed Mar
↓ 0
github:wojiao42/dsh-memory-file
File-backed memory: injects your own Markdown memory file at each session start, adds read
↓ 0
github:woshishadowhunter/dsh-seed-society
Memory consolidation tuning for dsh-mneme (autoDream enabled, schema-max output budget, de
↓ 0
github:wqx11235/dsh-experience
Local-first experience library for DeepSeek Harness: indexed markdown knowledge with error
↓ 0
github:WU079/dsh-memory-keeper
Cross-session memory for DSH: export every session to readable Markdown transcripts, keep
↓ 0
github:wu81313-lab/dsh-company-kb
Local-folder knowledge base for DSH: builds a SQLite FTS5 index over Office, text, PDF and
↓ 0
github:wuwen837/dsh-companion
Adds a Chat mode beside Work with a user-defined persona, long-term memory extracted after
↓ 0
github:wuying1630/dsh-selfmem
Three ledgers for a model that loses context between restarts. Self-note: what I have beco
↓ 0
github:WYR-233/dsh-memory-lite
Read-only enhancer for a file-based long-term memory library (markdown cards in git): a me
↓ 0
github:XHszDHM/dsh-memory-tide
Long-term notes and daily journals kept per workspace in a hot/cold archive, each tier wit
↓ 0
github:Xieddenv/dsh-memory-kit
Gives a DSH agent five layers of persistent memory kept as plain Markdown files — persona,
↓ 0
github:XinzeQing/dsh-user-memory
White-box memory in two parts: four user-authored long-term tiers (must-follow rules, beha
↓ 0
github:xiyunSacire/dsh-skill-manager
View and delete persistent skill memory from the DSH sidebar.
↓ 0
github:Xplore-LAB/dsh-plugin-asmemory
Action-state time memory: record typed states and actions, then analyze trends, anomalies,
↓ 0
github:xs1023/dsh-memory-vault
SQLite-backed long-term memory for DeepSeek Harness: add, search, update and archive entri
↓ 0
github:xulei666a/dsh-rules
Unified rules/guidelines layer for DeepSeek Harness. Keeps every agent guideline in one lo
↓ 0
github:yangyongzhen/dsh-memory
Long-term memory injected at session start: preferences/facts/summaries/knowledge in globa
↓ 0
github:Yansera/dsh-living-memoir
Cross-session memory kept as a short Markdown living document that is rewritten in full at
↓ 0
github:Yiipu/dsh-agentmemory
DSH ↔ agentmemory session-memory bridge: mirrors session lifecycle into a local agentmemor
↓ 0
github:Yuankilo/dsh-memory-studio
Memory for DeepSeek Harness with five sections (memories, tree, profile, graph, inbox), a
↓ 0
github:yuyolin/dsh-decision-log
Decision log for DeepSeek Harness: record key decisions (chosen option + why) into a versi
↓ 0
github:zhaoyuntao-wl/dsh-plugin-thread
Decision-and-goal memory with lineage: explicit commands and a model tool record decisions
↓ 0
"https://github.com/ZyxQl-Ala/dsh-decay-memory/releases/download/v0.3.0/dsh-decay-memory.tgz"
Agent memory with a forgetting curve: entries gain weight when mentioned, shrink when forg
↓ 0
github:LIU118117/dsh-love
Distills daily chats into an updatable character card and a cross-session emotion module t
↓ 0
github:liuyuhao1122/dsh-hermes-memory
Layered long-term memory for DeepSeek Harness with automatic model distillation, source-li
↓ 0
github:ljsysfurryACE/dsh-compaction
Compaction backend replacing LLM summarization with a deterministic semantic extractor (ke
↓ 0
github:ljsysfurryACE/dsh-memory-director
LLM-driven remember/forget memory: after each turn a model decides what to keep (MemoryDir
↓ 0
github:lishicheng2054/dsh-flavor-memory
Character-chat memory layer that keeps persona, voice and relationship state separate from
↓ 0
github:LingDangZaiXiang/dsh-life-hair
Copies the compaction checkpoint into the sticky-notes archive when context is compacted a
↓ 0