1
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Too many to read? See the shortlist of the 8 most-used memory context plugins — one page, ranked by stars.
Home/Categories/Memory & ContextToo many to read? See the shortlist of the 8 most-used memory context plugins — one page, ranked by stars.
Memory & Context
Memory layers, context managers and retrieval tools that give DSH agents persistent recall.
Persistence layers: vector stores, note systems, context compaction and retrieval helpers that keep an agent coherent past the first window. We track 29 repositories in this bucket, 4% of the 714 projects in the directory. Together they hold about 20.6k GitHub stars, though the median project sits near 161 — the headline number comes from a handful of very large repos, as usual in a young ecosystem.
By language the mix is JavaScript (12), TypeScript (11), Python (6); by license it is MIT (23), NOASSERTION (2). 28 of 29 have been pushed since August 2026, so the bucket is still moving. The three largest projects by stars are MemOS, memsearch, dsh-mnemon.
Match the store to your retrieval pattern: a notes system and a vector index solve different problems. Sort by last update rather than stars for anything you plan to depend on, and open the README before installing: a plugin that is three months stale may still work, but you want to know that going in.
Browsing the whole set instead? The full plugin index lists all 714 repositories with stars, language and last-update date in one table. Adjacent categories worth a look: UI & Themes, Models & Routing, Desktop Apps, Agents & Teams. If you are still choosing a runtime, read the install guide first.
What the data shows: all 29 projects analysed →
All 29 projects in Memory & Context
AllUI & ThemesModels & RoutingDesktop AppsAgents & TeamsMarkets & RegistriesSkills & LearningOtherMemory & ContextTerminal & CLIAwesome ListsWorkspace & FilesTools & IntegrationsWeb & BrowserChannels & BotsMonitoring
2
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
3
Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.
4
Deepseek Harness、Openclaw知识图谱记忆插件。2026年4月受邀发布在清华大学讨论会。Knowledge Graph + Memory；Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse
5
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.
6
白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。
7
Local long-term memory for Hermes, Codex, Claude Code, WorkBuddy and dsh agents: one SQLite store, source-backed recall, and tools to inspect, correct or delete what is remembered.
8
为 DeepSeek Harness 带来「跨会话长期记忆 + 后台自我进化」能力的纯插件实现：五轨记忆 · git 分支感知 · 回合内自我审查 · 技能自我进化与技能管理器 · 四轨待办 · COI 调度 · 会话广播 · 会话搜索 · 提示词管理器 · 临时信息便签——零核心修改、零运行时依赖，随装随用、卸载即净。
9
DeepSeek Harness (DSH) plugin: a live iOS Simulator — and a USB-connected iPhone — inside the conversation. 22 agent tools for booting, building, driving the UI by accessibility identity, OCR text or list rows, plus a streaming sidebar panel you can tap and drag on.
10
DeepSeek Harness 换肤 / 壁纸 / 主题包插件 (dsh-plugin) — 8 套 Mirage 主题、每用户强调色、壁纸2.0、主题包导入导出/分享链接、收藏与随机，纯原生 token 系统实现。
11
Import conversation history from 25+ AI coding agents into DeepSeek Harness as resumable sessions — tool calls, reasoning and results kept intact, with reverse export and sync. | 把 25+ AI 编程 Agent 的聊天记录导入 DeepSeek Harness 继续对话，保留工具调用、推理与结果，支持反向导出与同步。
12
A DeepSeek Harness (dsh) plugin — turns dsh web into a SillyTavern-style roleplay frontend: character cards, prompt presets, lorebooks, personas, BM25 long-term memory, world-state deltas, and rollback-able floor operations, all on the dsh agent runtime.
13
把 dsh 会话变成合规、可复现、可追责的 AI 投研工作台：ai-hedge-fund 回测 + risk-gate 风控 + cron 盯盘 + 记忆复盘 | compliance-first AI investment desk
14
DeepSeek Harness plugin for previewable cross-preset session migration. Fixed-schema handoffs preserve state, source-model intent, and unresolved images; the original session stays untouched.
15
Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.
16
Proactive associative memory for DSH: system-prompt recall before the model speaks, three-layer auto-consolidation, skill crystallization, and Astra-style context management - handoff ledgers, PLAN whiteboard, water-level sensing. Local-first, model-agnostic, zero deps. 主动联想记忆+Astra 式上下文管理：自动唤回/自动沉淀/技能固化/交接账本与白板跨窗口续命/水位感知。
17
Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.
18
implemement of DEEP SUPERVISED HASHING FOR FAST IMAGE RETRIEVAL_CVPR2016
19
dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。
20
Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.
21
Visual conversation map for DeepSeek Harness — sessions as cards on a whiteboard: drag to arrange, double-click to chat, draw an edge to fork with injected context. ADHD-friendly spatial memory. · DSH 可视化对话地图
22
DeepSeek Harness 任务清单插件：官方 todo_write 的增强 fork —— 优先级标签、完整清单渲染、可拖动的会话内浮动任务面板（位置记忆 / 双击复位 / 当前动作显示）
23
Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval
24
Knowledge base & RAG plugin for DeepSeek Harness (DSH): chunking, local embeddings, hybrid search, management panel
25
deepseek harness plugin obsidian memory
26
Third-party DSH WebUI enhancement plugin: custom backgrounds, theme colors, prompt presets, token/context visibility, and manual compact.
27
Hermes-style skill self-evolution plugin for DeepSeek Harness (DSH): crystallizes reusable agent skills from successful turns via signal-triggered LLM review, progressively improves them, and manages everything in a Settings panel.
28
Live balance & usage for every LLM provider, one glance away — a draggable floating ball for DeepSeek Harness / dsh 插件：可拖动悬浮用量球，一眼看清所有 Provider 余额与用量
29
Vision for text-only LLMs: multi-model failover vision API + drag-and-drop image recognition in the DSH web UI. Adapted from claude-vision-skill. 为纯文本模型补视觉能力 · 多模型自动降级