AI效率全能助手：按场景匹配工作流与跨会话记忆
AI效率全能助手（@user_41b104fd/ai-efficiency-booster）是 SkillHub 社区 Skill，v1.1.1，无需 API Key。覆盖职场办公、新媒体运营、数据分析、项目管理、创业副业，内置 50+ Prompt 与 20+ 自动化工作流，支持痛点识别、提效对比与跨会话记忆，并声明拒绝代写洗稿侵权。本文说明定位、核心能力，以及按 skillhub.md 用 skillhub install 安装到 Cursor 等 skills 目录的步骤与典型用法边界。
Read More跨会话记忆桥：让 AI 助理跨会话接续项目上下文
跨会话记忆桥（@user_41b104fd/context-bridge-pro，v1.0.3）是 SkillHub 社区 ai-agent 类 Skill，无需 API Key。它作为主动 Agent 在后台记录多项目的进度、决策与待办，支持模糊匹配、别名与自动发现新项目，便于跨会话、跨设备接着聊。安装需按 skillhub.md 使用 skillhub CLI，并用 --dir 指向 Cursor、Claude Code 或 Codex 等对应的 skills 目录。装上后可用「继续上次」或官方列出的中英文触发词接续上下文，适合多项目并行与长周期任务；存储与同步细节以 Skill 实际行为为准。
Read Moredsh-mnemos: Controlled Cross-Session Memory Plugin for DeepSeek Harness
The DSH plugin dsh-mnemos is purpose-built to address agents' "context loss" and disorganized memory management. It is a controlled, extensible cross-session memory plugin that ensures data security through a human approval queue and provides memory retrieval, batch distillation, skill transformation, and SQLite/Git-based storage synchronization. Supporting an open bus mechanism for third-party integration, it also offers a `/memory` command and API interface, aiming to build a long-term memory infrastructure for DSH agents.
Read MoreCross-Session Memory Management Plugin (Workspace Memory DSH)
Designed specifically for the DeepSeek Harness (DSH) architecture, this plugin addresses cross-session context loss in agents. It builds structured indexes from propositional graphs and a three-tier memory funnel, supports hybrid vector and lexical retrieval, and enables persistent management of project progress, task status, and decisions. It provides a browser-based review panel and a remote API, allowing agents to review and update memories, making it suitable for short-term project workflows.
Read MoreDeepSeek Harness (DSH) Cross-Session Memory Plugin
The DSH plugin `dsh-plugin-memory` is designed to address conversational context loss in long-cycle tasks. It adopts a two-tier memory structure (primary memory and topic files), persists information as Markdown files, and automatically injects it into new sessions. The plugin supports logging as work progresses, silent background distillation, project-level isolation, and content deduplication. Through seven tools (such as saving, retrieval, and writing) and hot-reloadable configuration, it helps the model maintain long-term state in unattended scenarios while providing comprehensive guardrail mechanisms.
Read MoreStrataGate Agent Memory: A Local Cross-Session Memory Plugin for DeepSeek Harness
StrataGate is a local memory management plugin for DeepSeek Harness, designed to address context window overflow and information dilution. It builds a retrievable memory store by automatically capturing conversations, with two components: short-term memory for detail retention and long-term memory for knowledge graphs and timelines. The plugin features evidence gating, on-demand reinforcement, and provenance tracking, and supports structuring imported content. Users can enable it by adding the plugin via a command, with data stored by default in a local database.
Read Moredsh-memory-s3: Cloud-Based Cross-Session Memory Plugin
This is a cloud-based cross-session memory plug-in designed for DeepSeek Harness, using S3-compatible storage (such as AWS S3 or MinIO) to enable persistent memory and cross-device sharing. It employs a structured memory model and supports semantic retrieval, local caching, backlink indexing, and file attachment management. To ensure security, all write operations are subject to mandatory approval gates. The plug-in has no GUI configuration; S3 credentials must be managed via environment variables, and it provides a set of tools for adding, deleting, updating, retrieving, and synchronizing memories.
Read Moredsh-memory: Cross-Session Memory and Vector Retrieval Plugin for DeepSeek Harness
`dsh-memory` is a cross-session memory plugin designed for DeepSeek Harness, aimed at resolving the loss of context after agent restarts. Maintained by developer zhouzhencheng07, it features core capabilities including automatic background memory, maintaining daily workspace notes, memory retrieval, and optional vector search. The plugin runs with the permissions of the current process; users are advised to review its source code and license before installation. It provides an effective solution for handling long-term memory in the DSH ecosystem.
Read MoreDeepSeek Harness Cross-Session Persistent Memory Plugin
`dsh-tool-memory` is a memory plugin for DeepSeek Harness, designed to address the loss of cross-session memory in agents. By injecting long-term memory into the system prompt as plain-text snapshots, it provides bounded, secure, and cross-session memory capabilities. The plugin supports frozen snapshot injection, six memory-manipulation tools, automatic background information consolidation, and security mechanisms such as injection-attack protection. After installation, users can manage memory through natural-language commands or configuration files, making it suitable for DSH applications that require long-term context maintenance.
Read Moredsh-trivium: In-process graph memory plugin for DeepSeek Harness
dsh-trivium is a process-in-memory graph memory plugin for DeepSeek Harness (DSH) based on TriviumDB, designed to solve the issue of agent memory not persisting across sessions, eliminating the need for external vector databases or independent services. It structures memory into four tools—ctx_find, ctx_read, ctx_remember, and ctx_link—with nodes categorized into Entities, Preferences, Decisions, and Experiences, while edges record associations. By default, the plugin operates quietly, injecting a compact graph of approximately 400 tokens into new sessions only once and querying the rest on demand. It supports manual editing for correction, strict write hygiene (filtering out garbage text and keys), optional embedding vector retrieval, and Git collaboration. It is installed via the `dsh plugin` command, utilizes one `.tdb` file per workspace, and fails without blocking.
Read More@max-null/dsh-memory: DeepSeek Harness's Cross-Session Plaintext Memory Plugin
# Introduction Using a harness like DSH for agent development, a common pain point is that nothing is retained between sessions: when you tell the model in the previous round that "This project uniformly uses Vue3 `<script setup>`", it forgets it in the new session. The common remedy is to stuff memory into a vector database and rely on similarity search—the penalty is that the memory itself becomes a string of unreadable numbers, and expired information is hidden in the database, making it unobservable and unfixable. `@max-null/dsh-memory` takes a different path: all memory is plaintext, retrieval uses deterministic BM25, and writing requires passing a manual confirmation gate. Below is an introduction to its design and usage. # What is this `@max-null/dsh-memory` is a cross-platform solution for DeepSeek Harness.
Read Moredsh-cue-bank: A Cross-Session Event Touchpoint Memory for DeepSeek Harness
# Introduction When using DSH (DeepSeek Harness) for development, sessions are isolated: if a topic discussed last week is raised again in a new session today, the agent cannot recall the details; similarly, if a topic is switched and then returned to within the same session, the key information may have already fallen out of context. Existing workarounds each have their limitations—`dsh-session-query` provides a passive query API that requires manual invocation; `dsh-session-reference` requires users to explicitly `@` mention relevant information; `dsh-agent-instructions` only loads static instruction files. None of them actively recall memory at the appropriate time. DSH's philosophy is "everything is a plugin," and capabilities such as cross-session memory can be...
Read Moredsh-goodmemory: Add automatic cross-session memory to DeepSeek Harness
dsh-goodmemory is a plugin for DeepSeek Harness (DSH) that provides cross-session long-term memory. Maintained by hjqcan, it utilizes GoodMemory as its backend. The plugin aims to address the lack of stable memory between DSH sessions by automatically recalling relevant memories prior to the model step (injected as an identifiable user message) and writing back the valid dialogue text of users and assistants after a successful turn, while excluding tool calls, reasoning processes, and injected content. The plugin supports two operating modes: the default "managed" mode automatically launches the goodmemory-http-bridge sidecar and uses SQLite for data storage, while the "external" mode connects to an existing GoodMemory instance.
Read Moredsh-layered-memory: DSH Cross-Session Long-Term Memory Plugin
dsh-layered-memory is a cross-session long-term memory plugin for DeepSeek Harness (DSH), licensed under the MIT License, designed to address the issue of context loss following a session. The plugin persistently stores verified facts, task experiences, and environmental information on disk, supporting cross-session retrieval. Core features include L1-L3 layered memory, namespace isolation, BM25 full-text search, content deduplication, and cross-namespace experience enhancement. The plugin provides 14 memory tools, such as `memory_write` (mandatory evidence verification), `memory_search`, and `memory_index`, and supports progressive tool exposure. Consistency maintenance relies on deduplication, manual updates, and candidate merging; the system does not automatically detect contradictions, and it is strictly prohibited to physically discard verified facts, allowing only compression.
Read MoreDSH Cross-session Memory Plugin dsh-memory: YAML Storage, Semantic Retrieval, and Two-level Injection
`dsh-memory` is an MIT-licensed cross-session memory plugin developed specifically for DeepSeek Harness (dsh), designed to address context loss issues in new sessions, such as the need to repeatedly explain project preferences and historical learnings. The plugin stores memories via YAML files (default `memory.yaml`) and provides six core tools—`remember`, `recall`, `view`, `list`, `forget`, and `pin`—to implement memory saving, mixed retrieval (keywords + local Ollama embedding), viewing, and lifecycle management. Its main features include adopting a "title-first" injection strategy to reduce token usage; and supporting `session` (fixed injection) and `auto` (on-demand injection).
Read Moredsh-memory-vault: A Cross-Session Memory Vault for DeepSeek Harness
dsh-memory-vault is a cross-session memory plugin developed for DeepSeek Harness (DSH), designed to solve the problem that information such as project preferences, deployment constraints, and test commands is confined to a single conversation context and cannot be persistently reused. The plugin provides three core model tools — `memory_remember`, `memory_recall`, and `memory_forget` — and persists memory data in the DSH storage domain. Its main features include: automatically injecting recent memory entries at each system prompt assembly to maintain contextual continuity; scoring and ranking recall results based on tag and content matching; and providing a browser-based management entry through the Settings page, allowing users to intuitively browse, add, and delete memories. The plugin is simple to install, requiring only
Read Moredsh-biomemory: Cross-Session Memory Plug-in for DeepSeek Harness
dsh-biomemory is a cross-session bio-inspired memory plugin for DeepSeek Harness (DSH), designed to address the issue of context loss in multi-turn tasks. It expands memory from individual logs into a structured management system through hierarchical storage, approval gating, semantic retrieval, memory metabolism, and audit snapshots. Built on SQLite and a local embedding model (bge-small-zh-v1.5), the plugin supports exact keyword, semantic vector, and hybrid retrieval, and automatically degrades to keyword retrieval when the model is unavailable. Core capabilities include frozen snapshot injection to reduce preference-guessing costs, manual approval and demotion strategies for important memories, and half-life decay, reference consolidation, and conflict surfacing via the "Dream" mechanism. Additionally, the plugin provides complete audit logs, backup recovery, and single-entry rollback functionality, with support for importing from Markdown.
Read MoreEquip DeepSeek Harness with Readable and Editable Cross-Session Memory Using dsh-mneme
dsh-mneme is a DeepSeek Harness memory plugin maintained by modusensus, licensed under MIT. It uses native SQLite with editable Markdown for dual-writing cross-session memory, and offers autoDream background consolidation and optional offline semantic retrieval. This article verifies the installation commands, seven memory_* tools, configuration options, and notes based on the community directory page and GitHub README: the plugin runs with current dsh privileges, requires Node 24+, and has entity extraction and Sleep Mode disabled by default.
Read More