dsh-governed-memory:DeepSeek Harness 的治理型长期记忆插件
`dsh-governed-memory` 是面向 DeepSeek Harness (DSH) 的治理型长期记忆插件,由 `haoyuan-sjtu` 维护,许可证为 MIT。其核心旨在解决智能体长期记忆中记录来源、权限、范围及撤销等治理问题,通过约束 capture、promote、revoke 和 retrieval 流程,减少模型随意写入与检索注入的风险。 该插件不提供浏览器 UI 或 HTTP 端点,仅作为 DSH 进程内的可信 host plugin 运行。它关闭了模型侧的直接写入入口,规定候选记录初始进入隔离区(quarantine),需经可信 host 显式批准及证据验证后方可
Read Moreimemory:DSH 自进化长期记忆插件
imemory 是 DSH 的一个 MIT 许可插件,旨在解决多会话中上下文不足导致长期信息丢失的问题。它通过回合后自动提取值得保留的信息并打分,在每一步前通过关键词初筛和 LLM 语义重排召回相关记忆注入上下文。核心功能包括:新会话开场注入用户档案、每 6 小时进行冲突合并与衰减淘汰、将可复用流程沉淀为 `learned-*` 技能,以及提供 6 个记忆管理工具和 `/imemory/` 网页管理面板。该插件零依赖,不挑 profile 类型。 安装需 DSH 版本 0.1.0-rc.6 及 Node >= 20。支持手动挂载(复制文件并修改 `cordis.patch.yml`)或 bun
Read Moredsh-memory:DeepSeek Harness 的长期记忆插件
dsh-memory 是面向 DeepSeek Harness (DSH) 的 MIT 许可长期记忆插件,旨在解决多会话工作中用户偏好、验证步骤及失败教训缺乏稳定载体的问题。它通过 GitHub 分发,利用结构化抽取将已完成会话中的可复用信息转化为摘要与记忆文件,并自动注入后续会话。核心功能包括:会话结束后的防抖抽取(默认3分钟)、全局冷却整合(默认6小时)至 MEMORY.md 与 memory_summary.md、摘要常驻注入,以及提供 memory_list、memory_read、memory_search、memory_add 四个查询与添加工具。其中 memory_add 仅在用
Read Moredsh-noc-memory:给 DeepSeek Harness 接入长期记忆的插件
dsh-noc-memory 是 DeepSeek Harness(DSH)的一个插件,旨在解决智能体单次会话结束后上下文丢失的问题,实现长期记忆功能。该插件并不提供独立的记忆库,而是将 DSH 连接到用户自部署的 Noc Memory MCP 服务器上。它主要提供两类能力:一是会话开始时的长期记忆加载(noc_boot)与每日简报(noc_briefing);二是对记忆条目的读取、搜索、创建和更新(noc_read, noc_search, noc_create, noc_update)。 使用该插件需满足 Node.js >= 20.0.0 的环境要求,并通过 dsh plugin --p
Read Moredsh-agent-memory:为 DSH 提供智能体驱动长期记忆
dsh-agent-memory 是为 DeepSeek Harness (DSH) 打造的 MIT 许可长期记忆插件(v0.3),旨在提供跨会话的结构化记忆能力。它采用分层存储架构,将记忆划分为 L1 事实(偏好与环境)、L2 知识(可复用内容)、L3 情景(经历时间线)及摘要层,并支持全局与工作区两种作用域路由。插件向智能体暴露 remember、recall、memory_browse、update/forget 及 memory_stats 等工具,支持多维度检索与时间金字塔浏览。其特色功能包括时间桶自动压缩以及与 dsh-agent-compact 联动,在会话压缩后自动沉淀 che
Read Moreinterest-memory:为 DeepSeek Harness 增加跨会话长期记忆
interest-memory 是由 djasdh 维护的本地长期记忆服务,旨在解决 DeepSeek Harness (DSH) 会话间上下文不连续的问题。该服务基于 Go 语言开发,利用 SQLite-vec 向量索引实现本地存储与检索,支持完全离线运行。它通过 Cordis 插件 `@djasdh/interest-memory-dsh-bridge` 接入 DSH,在会话开始时自动召回相关记忆,结束时推送对话记录。核心功能包括带证据的记忆存储、三阶段验证(检查/声明/矛盾)、语义相似条目的自动合并、旧条目的取代标记以及基于图谱的查询可视化。系统提供 REST API 供多代理框架共享使
Read MoreDSH ExpMem:为 DeepSeek Harness 增加可检查的长期记忆插件
DSH ExpMem 是面向 DeepSeek Harness 的 MIT 许可社区插件,旨在解决长期个人记忆的本地存储与追溯问题。它将用户习惯、任务经验和工程洞察写入本地 JSON 文件,保留 DSH Session 作为原始逐字历史层,且不复制 Session 事件。该插件采用分层记忆架构,支持在上下文压力大时提示 Agent 保留持久知识,并基于相关性、近期性和重要性进行检索排序。其核心优势包括支持可审计的反思(引用支撑观察、可中断恢复)、维护候选至弃用的完整信任生命周期、以及导入 Claude Code 和 Codex 的 Markdown 记忆为带来源证据的候选记录。插件运行轻量,不
Read Moredsh-llmwiki:DeepSeek Harness 的本地 Markdown 长期记忆插件
dsh-llmwiki 是由 chancelu 开发并维护的一个 DSH 插件,旨在解决智能体模型上下文窗口有限及长期记忆缺失的问题。它将本地 Markdown vault 作为 DeepSeek Harness 的长期记忆存储,通过向模型请求注入相关 Wiki 知识实现持续利用。该插件提供 `memory_search` 和 `memory_save` 工具,支持自动捕获每日会话至指定目录,并采用关键词、维基链接图及时间戳三种检索策略,结合 RRF 算法融合结果,在 token 预算内组装上下文。它具备 LRU + TTL 缓存机制,除 Node.js(需 22 及以上版本)外无其他运行时依
Read Moredeepseek-harness-memory:DSH 的 Claude Code 风格长期记忆插件
deepseek-harness-memory 是 DSH 社区的一款长期记忆插件,由 2303572348 维护,采用 MIT 许可证。该插件旨在提供跨会话持久记忆能力,并将数据以纯 markdown 文件(含 YAML frontmatter)形式存储,与 Claude Code 记忆格式完全兼容。 核心功能包括:支持用户级和工作区级记忆存储,并在会话启动时自动将记忆索引注入系统提示词;提供 memory 工具用于记忆的增删改查及从 Claude Code 导入记忆;支持通过 projectAliases 将多 checkout 映射至统一项目记忆。插件可通过 cordis.patch.y
Read MoreAgentSoul:DeepSeek Harness 的本地人格与长期记忆插件
AgentSoul 是 DeepSeek Harness 的本地插件,旨在为 Agent 提供稳定的人格、身份、状态及长期记忆层。该插件以 bundle 形式安装,启动时自动全局加载,要求 Node.js >=22.5.0,采用 MIT 许可证。其核心能力包括支持 SOUL、IDENTITY、USER、STATE 四层人格文件(具备写入保护),以及基于 SQLite 的本地长期记忆与蒸馏机制,当 SQLite 不可用时自动降级为 JSON 存储。插件具备异常隔离特性,确保自身故障不阻断主 Agent 循环,并注册了状态查看、记忆搜索和手动蒸馏等 6 个模型可见管理工具。安装通过 `dsh pl
Read Moredsh-soul-md:为 DeepSeek Harness 提供人设卡与长期记忆
dsh-soul-md 是 DeepSeek Harness (DSH) 的社区插件,旨在通过设置界面集中管理人设与长期记忆,避免手动维护散落文件。其核心功能包括“人设卡”和“长期记忆”:人设卡内容渲染至 system prompt,支持多卡片、按会话或工作区切换,并允许 AI 通过工具读写演化;长期记忆提供持久化存储,注入 prompt 时受大小限制,且优先关联当前激活的人设卡。安装需 Node.js >=20.18,新版插件要求 DSH >=0.1.0-rc.7,旧版用户需锁定特定版本。使用上,用户可在设置页创建卡片并指定默认值,AI 则利用专用工具自主管理记忆与人设。该插件适用于需在不同
Read Moredsh-plugin-meta-memory: Structured Long-term Memory for DeepSeek Harness
The dsh-plugin-meta-memory is a plugin in the DSH ecosystem designed to address issues of dispersed long-term memory and context reuse. It organizes memory into a "unit + record" structure, where each record distinguishes between `brief` (summary) and `full` (complete content), supports automatically injecting relevant `brief` into the Agent context, and maintains a global `index` to organize clues. The plugin provides a CLI tool `mm` that supports operations such as initialization, list viewing, reading, searching, and index management, allowing users to name units in a `verb-modifier-noun` format, enabling hierarchical storage and on-demand loading of memory. Its main features include memory classification, quick summary scanning, full record retrieval, and automatic context injection. Configuration options include `m
Read Moredsh-task-memory: Task-Isolated Long-Term Memory for DeepSeek Harness
`dsh-task-memory` is a MIT-licensed long-term memory plugin for DeepSeek Harness, designed to address the issue of task content confusion caused by global memory. This plugin uses tasks as isolation boundaries, maintaining independent memory banks for each task to ensure that `remember`, `recall`, and `search` operations are performed only within the scope of the current task. Core features include binding specific task banks via `memory_bind_task`, providing precise read/write operations by key and lexical search based on keywords (supporting both Chinese and English), supporting memory deletion and bank management, and optionally injecting the current task's pinned or recent facts into the agent's system prompt to optimize context. The plugin requires Node.js >= 20.
Read Moredsh-memory: Integrating LingShu Long-Term Memory into DeepSeek Harness
dsh-memory is a DSH memory plugin maintained by FuRongJun-1999 that integrates the LingShu (AEIS) Spatiotemporal Memory Engine into DeepSeek Harness. It provides cross-session recall/search, a knowledge flywheel, a white-box reasoning pipeline, self-awareness, and a v3.3 role-playing engine, along with a guardrail charter and full-chain audit. Installation requires first installing aeis via pip, then adding the plugin using `dsh plugin --profile` and configuring `dbPath` and `tools` mode in `cordis.yml`. It is suitable for AGI and interpretability research-oriented developers. Before use, please review the source code and the MIT license.
Read Moredsh-memory: Providing Local Git Long-Term Memory for DSH
dsh-memory (seriousz158/dsh-memory) is a local Git long-term memory plugin for DeepSeek Harness. Memory is stored in a separate Git repository instead of the cloud, and injection is controlled via the memory.enabled setting. The settings page allows for status viewing and secure clearing, with optional idle session synchronization. Installation: dsh plugin --profile web add github:seriousz158/dsh-memory. Compatible with DSH 0.1.0-rc.6/rc.7, licensed under MIT.
Read MoreDSH Noema: Installing Viewable Long-Term Memory for DeepSeek Harness
dsh-noema is a Noema long-term memory plugin developed by ZSeven-W for DSH. It integrates local-first, non-vector memory into Agents, providing noema_* tools such as recall, retrieval, and import, along with a web-based settings page. Memories are stored in Markdown format in the ~/.agent-memory directory and can be migrated from tools like Cursor, Claude Code, and Codex, with support for service keep-alive. This article introduces its positioning, features, installation commands, and usage considerations.
Read Moredsh-memory-evolve: Equipping DeepSeek Harness with Long-Term Memory and Self-Evolution
dsh-memory-evolve is a DSH memory-type plugin maintained by csyangwen, which provides capabilities such as five-track cross-session memory, git branch awareness, four-track to-do lists, skill self-evolution, COI external AI scheduling, and session collaboration in a purely plugin-based manner, with zero core modifications and zero runtime dependencies. This article introduces its positioning, core features, installation commands, and typical usage, while also explaining community directory attributes and security considerations.
Read MoreAdd Cross-Session Long-Term Memory to DeepSeek Harness with dsh-memory-evolve
`dsh-memory-evolve` is a DeepSeek Harness memory plugin maintained by csyangwen (MIT License, JavaScript). It uses five-track memory, git branch filtering and confirmation-based writing to沉淀 project conventions, user preferences and progress into `~/.dsh/memories/`, eliminating the need to repeat everything from scratch when switching sessions. Capabilities such as skill evolution, four-track todo, COI scheduling and session broadcasting are also provided in the same repository, and most of them are disabled by default. The installation command on the directory page is `dsh plugin add github:csyangwen/dsh-memory-evolve`. The community plugin library has no official affiliation with DeepSeek / Horizon Robotics (Fang), and you should check the source code and license before installing.
Read More