DeepSeek-OCR based optical compression memory plugin that renders memories as images for storage, degrades resolution by age, and automatically restores them in HD for retrieval.
- Language
- JavaScript
- License
- MIT
- Branch
- main
Install
$ dsh plugin --profile web add github:DDDFXYqiming/Agent_Extensions#path:dsh-plugins/dsh-ocr1-memoryRun the command above in your terminal to install this plugin via the dsh CLI. You can switch Profile in the top-right corner. New to dsh? Read the beginner tutorial
Install via your agent
Install the DeepSeek Harness plugin DDDFXYqiming/Agent_Extensions/dsh-plugins/dsh-ocr1-memory for me: review the repository at https://github.com/DDDFXYqiming/Agent_Extensions first, then run the install command and verify the plugin loads successfully.
Paste this instruction to the DSH Web GUI assistant — it will install and verify for you.
One-Line Positioning
Store DSH Agent memories as "images" instead of plain text: each memory is rendered as a numbered PNG, older memories automatically downscale in resolution by age, and when retrieval hits a memory, DeepSeek-OCR reads back the original text fragment.
Core Capabilities
- Text entry automatically segmented and rendered as images (with SoM numbering), stored in local memory store
- Automatic resolution reduction by age: vivid(1280px, within 24h) → normal(1024px, within 7 days) → fuzzy(640px, older)
- Active recall temporarily restores HD when retrieving low-res memories
- Use OCR to read back images as retrieval evidence, returning original text fragments instead of generative summaries
- Store 1280-dimensional visual vectors (DeepSeek-OCR embeddings), using cosine similarity as the primary retrieval signal
- Provide 9 tools directly callable by Agents: status/store/update/retrieve/list/compression ratio metric/baseline calibration/delete/render and embedding self-test
Technical Implementation
- Language: JavaScript (Node ESM, zero runtime dependencies)
- Key Dependencies: @deepseek-ai/dsh-tools (register Agent tools), @deepseek-ai/schemastery (configure schema), Python + Pillow (image rendering); optional DeepSeek-OCR backend (vLLM or llama.cpp GGUF) for reading back and embedding
- Architecture Pattern: Mount 9 ocr1_mem_* tools to host tools service via
inject=['tools']; configuration injected via cordis.patch.yml;apply(ctx, config)builds renderer + OCR client + embedding client at startup, and can automatically start llama-server on demand - Entry Files: lib/index.js (apply entry registers all tools), lib/core.js (memory engine, retrieval algorithm, rendering pipeline), lib/ocr-server.js (llama-server lifecycle)
Use Cases
Suitable for scenarios requiring DSH Agent to have "persistent + long-term + visualizable" memory, such as letting Agents remember document key points, project knowledge, user preferences, and retrieve original text fragments on demand in multi-turn conversations. If only lightweight text memory is needed, the official dsh-memory is simpler; if you want memories to naturally "fade" over time and be able to OCR-read back image evidence, this plugin provides capabilities that the official memory lacks.
Prerequisites and Compatibility
| Dependency | Minimum Version | Description |
|---|---|---|
| Node.js | >=22.19.0 | engines.node declared |
| @deepseek-ai/cordis | >=4.0.0-rc <5 | peerDependencies |
| @deepseek-ai/dsh-tools | >=0.0.1-rc <2 | peerDependencies |
| @deepseek-ai/schemastery | >=3.18.0 <4 | peerDependencies |
| Python + Pillow | Any available version | scripts/render_memory.py dependency, Pillow needed locally |
| Platform | Cross-platform | OCR auto-start script defaults to Windows path, can override serverPath/modelDir |
| Native modules | None | Pure Node + Python subprocess, no node-gyp dependency |
Installation
dsh plugin --profile web add github:DDDFXYqiming/Agent_Extensions#path:dsh-plugins/dsh-ocr1-memory
Configuration Options
| Config | Type | Description | Default |
|---|---|---|---|
| storeDir | string | Memory store root directory, stores images and memories.json | <home>/.dsh/ocr1-memory |
| ocrBaseUrl | string | DeepSeek-OCR OpenAI-compatible endpoint (e.g. vLLM http://127.0.0.1:8000/v1), empty skips OCR readback | empty |
| ocrApiKey | string | OCR endpoint API key, usually empty for local services | empty |
| ocrModel | string | OCR model name | deepseek-ai/DeepSeek-OCR |
| pythonPath | string | Python interpreter for rendering script | python |
| renderScript | string | Absolute path to rendering script | <plugin dir>/scripts/render_memory.py |
| requireOcr | boolean | When true, OCR unavailability throws error instead of degrading | false |
| useMockRenderer | boolean | When true, skip Python, use pure text placeholder (self-test only) | false |
| autoStartOcrServer | boolean | When true, plugin automatically ensures llama-server is online after loading | false |
| ocrServerPath | string | llama-server executable path | Windows default or OCR_SERVER_PATH env var |
| ocrModelDir | string | DeepSeek-OCR GGUF directory | Windows default or OCR_MODEL_DIR env var |
| ocrServerPort | number | OCR service port | 18080 |
| ocrEmbeddingBaseUrl | string | Visual embedding endpoint, empty falls back to ocrBaseUrl (combined mode) | empty |
| ocrEmbeddingApiKey | string | Embedding endpoint API key | empty |
| ocrEmbeddingModel | string | Embedding model name, empty uses ocrModel | empty |
| ocrEmbeddingTimeoutMs | number | Embedding request timeout | 120000 |
| ocrEmbeddingAutoStart | boolean | Whether to auto-start for independent embedding service | false |
| ocrEmbeddingPort | number | Independent embedding service port (not used in combined mode) | 18084 |
| ocrEmbeddingUbatchSize | number | llama-server -ub parameter, must be ≥ visual tokens per image | 2048 |
| ocrEmbeddingOnDemand | boolean | Not enabled in combined mode (only effective for independent service) | true |
| ocrEmbeddingIdleTimeoutMs | number | Embedding service auto-shutdown after idle milliseconds | 300000 |
| sharedStore | boolean | When true, reread memories.json before each operation, supports multi-Agent sharing | false |
| embeddingRetrieval | boolean | When true, use 1280-dim visual embedding similarity as primary retrieval signal | true |
| ocrMaxEntriesPerRetrieve | number | Max memories to OCR-readback when text retrieval insufficient, prevents large库 freezing | 5 |
| ocrRepeatPenalty | number | OCR readback repeat penalty coefficient | 1.2 |
| ocrNoRepeatNgramSize | number | OCR readback n-gram repeat suppression window | 30 |
| ocrTextOnlyPromptTokens | number | OCR text baseline (for estimating visual token count) | 5 |
FAQ
Q: How is this plugin different from official dsh-memory?
A: dsh-memory stores memories as plain text; dsh-ocr1-memory renders each memory as an image with SoM numbering, downscales to 640px fuzzy layer over time, and automatically active-recalls to restore HD when hitting low-res memories. It uses OCR readback instead of pure text retrieval, returning original text fragments instead of generative summaries, avoiding LLM hallucinations.
Q: Can I use it without DeepSeek-OCR service?
A: Yes, you can install and use ocr1_mem_status / ocr1_mem_store / ocr1_mem_list and other basic functions. But ocr1_mem_retrieve's image readback and visual embedding require an OpenAI-compatible OCR endpoint (vLLM running deepseek-ai/DeepSeek-OCR, or llama.cpp running GGUF version), otherwise retrieval can only use pure text scoring.
Q: What local environment is needed for rendering?
A: Python 3 plus Pillow library required. The plugin uses scripts/render_memory.py to call Python to render memory segments as PNGs (with SoM number boxes). The script has built-in CJK font candidate paths (Microsoft YaHei/PingFang/WenQuanYi), covering Windows, macOS, and Linux.
Q: Where are memories stored? How to delete individual memories?
A: Default location is <home>/.dsh/ocr1-memory/, can be changed to custom directory via storeDir config. Use ocr1_mem_forget tool to delete by id; uninstalling the plugin doesn't auto-clean that directory, manual deletion required.
Q: Why do older memories become blurry? Is this a bug?
A: Not a bug, it's by design: each memory falls into vivid(within 24h 1280px) / normal(within 7 days 1024px) / fuzzy(older 640px) tiers based on createdAt. When retrieval hits low-res tier, it automatically active-recalls to restore HD and grants temporary immunity from further decay within the window, simulating "human memory becomes clearer when recalled."
Q: Can multiple Agents share the same memory store?
A: Yes, set sharedStore to true. This mode rereads memories.json before each operation and uses unique temporary files + rename for serialized writes to avoid concurrent overwrites; test reports M1-M6 include multi-Agent sharing scenarios.
Q: How is visual token count measured?
A: The plugin measures visualTokensDirect via embedding endpoint's marker-only request (only sends media, no text), using text baseline for approximation. This is a measurement of llama.cpp's public interface, not DeepEncoder's internal tensor output; README clearly states this is an engineering approximation of the paper's idea.
Q: Can DSH Agent directly call these tools after installing the plugin?
A: Yes. The plugin registers 9 ocr1_mem_* tools to the host via inject=['tools'], Agents can call them directly in conversations without additional enable flags; tool output schema is strict, won't report invalid output under headless profile.
Difficulty Level
Advanced — requires local Python+Pillow installation, and OCR endpoint (vLLM or llama.cpp GGUF) must be truly online for retrieval and visual embedding to work; 27 configuration items total, relatively high barrier for users who just want "install and use."
Known Issues and Limitations
- OCR backend is engineering approximation, not paper reproduction: README lines 138-170 clearly state that DeepEncoder internal tensor output and "model outputs SoM number" from Locate-and-Transcribe cannot be implemented under current llama.cpp public interface, requires LoRA fine-tuning for further alignment
- Default path binds to Windows: lib/ocr-server.js:8 and lib/index.js:80-93 hardcode llama-server path as
D:\AI_Projects\models\llama.cpp\llama-server.exe, macOS/Linux users must override viaocrServerPath/OCR_SERVER_PATHenv var - ocrEmbeddingUbatchSize must be ≥ visual tokens per image: Default 2048 covers it, but shrinking to default 512 will cause llama-server to reject large images (README lines 128-131)
- Embedding service auto-shuts down after idle: Defaults to stop after 5 minutes idle (lib/index.js:153-160), high-frequency multi-Agent scenarios may repeatedly start/stop
- Retrieval text scoring is character-level token overlap: Chinese splits by single character, English by space, punctuation and emoji stripped; long queries not automatically rewritten
- Locate-and-Transcribe uses text scoring + OCR evidence instead of model output numbers: Returns verbatim fragments to avoid generation hallucination, but differs from OCR-Memory paper's original Locate path (README lines 145-147)
- Multi-modal embedding depends on llama.cpp extension: Cannot switch to official DeepEncoder output in AMD without NVIDIA/vLLM environment (README line 166)
- Python rendering 30s timeout: lib/core.js:267 sets 30s limit for single render, extra long text gets hard-wrapped to avoid single image timeout
简体中文 | English
Agent_Extensions
📦 DSH 插件已拆分为独立仓库
本仓库
dsh-plugins/下的 DSH 插件已迁移为独立 GitHub 仓库,推荐直接安装独立仓库:
插件 独立仓库 dsh-vision-skill https://github.com/DDDFXYqiming/dsh-vision-skill dsh-layered-memory https://github.com/DDDFXYqiming/dsh-layered-memory dsh-annotation-patched https://github.com/DDDFXYqiming/dsh-annotation-patched dsh-side-panel-patched https://github.com/DDDFXYqiming/dsh-side-panel-patched dsh-ocr1-memory https://github.com/DDDFXYqiming/dsh-ocr1-memory 安装示例:
dsh plugin --profile web add github:DDDFXYqiming/dsh-ocr1-memory本仓库不再维护 dsh 插件,仅保留历史快照与说明;后续更新请以独立仓库为准。
DeepSeek Harness(DSH)插件与 AI Agent 技能集合 —— 面向 DeepSeek Harness 的原生插件(走官方扩展接缝,零框架补丁)+ 跨框架通用 Skill + Hermes 插件,开箱即用。
本仓库收集、翻译并自包含封装 AI Agent 相关的技能资源,并面向 DeepSeek Harness(DSH) 提供标准插件形式的扩展。所有内容均为自包含(技能/插件内自带脚本、模板与文档,不依赖仓库外文件),克隆即可用。
✨ 内容总览
1️⃣ DSH 原生插件(dsh-plugins)—— 零框架补丁
面向 DeepSeek Harness 官方扩展接缝(ctx.skills / ctx.tools / ctx.credentials / ctx.slots / ctx.layout),可随 DSH 版本升级:
| 插件 | 能力 | 依赖 |
|---|---|---|
dsh-vision-skill v0.4.4 | 识图插件:8 个工具(含渐进式暴露激活工具)+ Credential 化 + 路径围栏 | Node.js + DSH(dsh-tools / dsh-credentials)、Python 3 + Pillow、视觉模型 API Key |
dsh-layered-memory v0.4 | 跨会话长期记忆:命名空间隔离 + L1 索引注入(存在性编码、KV 缓存友好)+ L2 环境事实 + L3 任务经验 + 自动蒸馏候选 + 溯源/归档/回滚 + 自动维护 | Node.js + DSH(dsh-tools) |
dsh-annotation-patched | 选中批注/引用插件(fork 增强):选中助手回复文字 → 批注(可空)或一键「引用」→ 回车随消息发送,回复按 Annotation N 逐条对照;增强:Codex 式「引用」按钮(显式确认制)+ 幽灵引用修复 | Node.js + DSH(纯浏览器端 bundle,零 Node 逻辑) |
dsh-side-panel-patched | 右侧工作区面板(fork 增强):文件树/多文件 tab/预览/编辑(CodeMirror)+ Git 审查 + 终端;增强:绕开官方 520px 宽度上限、头部像素级对齐、Codex 风格梭形拖拽把手、文件 tab 栈 + 会话跟踪、Windows 终端防崩溃 | Node.js + DSH(文件/Git/终端 API + 浏览器 bundle) |
dsh-ocr1-memory v0.1.0 | 光学压缩记忆:文本渲染为 SoM 图像存储 + 年龄衰减 + active recall + OCR 驱动召回 | Node.js + DSH(dsh-tools / cordis / schemastery)、Python 3 + Pillow、可选 DeepSeek-OCR 后端 |
2️⃣ 通用技能(General_skills)—— 跨框架可用
任何智能体框架(Claude Code / Codex / opencode / DSH / Hermes 等)均可把目录作为 Skill 挂载:
| 技能 | 能力 | 依赖 |
|---|---|---|
vision-skill | 识图:本地图片 → 视觉模型描述(Qwen 动态分辨率方法,OpenAI 兼容接口) | Python 3 + 视觉模型 API Key |
video-notes-generator | 视频 URL → 结构化 Markdown 笔记(时间戳 / 抽取帧 / 多模态图像观察 / AI 总结),支持 Bilibili / YouTube / 抖音 / 快手 / 本地文件 | Python 3 + 依赖(见 scripts/install_deps.sh) |
ppt-master | 源文档(PDF / DOCX / URL / Markdown)→ 多角色协作生成 SVG 页面 → 导出 PPTX | Python 3(标准库为主,可选依赖见 requirements.txt) |
markitdown-skill | 微软 MarkItDown:PDF / DOCX / PPTX / XLSX / HTML / EPUB 等 → 统一 Markdown | Python 3 + pip install -r requirements.txt |
generic-agent-code-run | GenericAgent 风格 code_run:Windows 桌面应用 / 真实浏览器自动化(Win32 / UIA / OCR / 截图 / CDP)+ 观察-行动-验证循环 | Python 3 + 对应库 |
所有技能均内置
SKILL.md(agent 运行时加载的指令),部分附scripts/、templates/、references/。
3️⃣ Hermes 插件(hermes_plugins)
| 插件 | 能力 | 依赖 |
|---|---|---|
language-router v5.0 | 自适应语言路由:Planner-first → Worker → 可选 Verifier → Digest 流程(NousResearch / Diana 出品),hooks 挂载 pre_llm_call / pre_api_request / post_api_request | Hermes 框架 |
📁 目录结构
Agent_Extensions/
├── dsh-plugins/ # DeepSeek Harness(DSH)原生插件
│ ├── dsh-vision-skill/ # 识图插件 v0.4.4(8 工具 + 渐进式暴露 + Credential 化)
│ ├── dsh-layered-memory/ # 分层长期记忆(v0.4:命名空间/自动蒸馏/自动维护)
│ ├── dsh-annotation-patched/ # 选中批注/引用插件(fork 增强,Codex 式选中即引用)
│ ├── dsh-side-panel-patched/ # 右侧工作区面板(fork 增强,多文件 tab + 会话跟踪)
│ └── dsh-ocr1-memory/ # 光学压缩记忆(SoM 图像 + active recall)
├── General_skills/ # 通用智能体技能(跨框架,挂载即用)
│ ├── vision-skill/ # 识图
│ ├── video-notes-generator/ # 视频转结构化笔记
│ ├── ppt-master/ # 文档 → SVG → PPTX
│ ├── markitdown-skill/ # 任意文档 → Markdown
│ └── generic-agent-code-run/ # Windows 桌面/浏览器自动化
├── hermes_plugins/ # Hermes 框架插件
│ └── language-router/ # 语言路由(planner-first)
└── README.md
🚀 快速开始
方式一:安装 DSH 插件(以 dsh-vision-skill 为例)
DSH 插件已拆分为独立仓库,推荐直接安装独立仓库:
# 1. 从独立仓库安装(自带 cordis.patch.yml,自动贡献 id: vision-skill)
dsh plugin --profile web add github:DDDFXYqiming/dsh-vision-skill
# 2. 配置 Credential($DSH_HOME/.credentials.yaml)
VISION_API_KEY: sk-xxxx
本仓库
dsh-plugins/下保留的是历史快照;各插件最新文档见对应独立仓库。
⚠️ bundle 安装后不要在 profile 的
cordis.patch.yml里再insert同名条目,否则会触发duplicate loader entry id启动崩溃;需要自定义配置时用裸条目按 id 覆盖(见插件 README)。
方式二:挂载通用技能(任何框架)
以 vision-skill 为例:
# 1. 复制技能目录到你的 agent 的 skills 目录
# (Claude Code: ~/.claude/skills/ ;Codex: ~/.codex/skills/ ;其他框架见其文档)
cp -r General_skills/vision-skill <你的 skills 目录>/
# 2. 配置视觉模型(OpenAI 兼容接口)
cd General_skills/vision-skill
cp templates/.env.example .env # 填入 VISION_API_URL / VISION_MODEL / VISION_API_KEY
# 3. 自检
python scripts/vision.py --check
其他技能用法详见各目录内 SKILL.md。
方式三:安装 Hermes 插件
将 hermes_plugins/language-router 目录放入 Hermes 插件目录即可(plugin.yaml 声明了全部 hooks 与版本信息)。
🧩 DSH 插件能力一览
dsh-vision-skill v0.4.4(8 工具 + 1 运行时 skill)
| 工具 | 能力 |
|---|---|
vision_analyze | 识图(5 模式 + mega 超高清 16M 像素预算) |
vision_ocr / vision_long_screenshot_ocr | 独立 OCR / 超长截图分块 OCR(带重叠切块 → 逐块识别 → 合并) |
vision_ground / vision_detect | 目标定位 / 元素枚举(像素坐标框 + 归一化坐标) |
vision_dominant_colors | 主色分析(本地像素算法,无需 API) |
vision_clipboard | 剪贴板图片兜底(应对"当前模型不支持图片"粘贴拦截) |
vision_activate | 渐进式暴露兜底:skill 加载后工具未自动出现时调用一次 |
工程化特性:渐进式工具暴露(全局只挂 1 个轻量激活工具,省上下文)、密钥 Credential 化(credential: VISION_API_KEY 引用,每操作解析)、路径围栏(realpath 校验防穿越)、超时与并发门控、严格 JSON Schema 结构化输出。
dsh-layered-memory v0.4(分层长期记忆)
| 组件 | 说明 |
|---|---|
memory:index 注入 | 通过 ctx.systemPrompt.context 每轮实时注入 L1 索引(存在性编码,读文件即生效,KV 缓存友好) |
memory(运行时 skill) | 触发语义:何时读 / 何时写 / 何时同步索引 |
memory_activate | 渐进式暴露兜底:skill 加载后工具未自动出现时调用一次 |
memory_list / memory_read | 列出 / 读取记忆(index / fact / sop,含溯源 meta) |
memory_write | 写入记忆(fact/sop,evidence 必填 = 行动验证公理) |
memory_index | 重建 L1 索引自动段(保留 [RULES] 手动段) |
memory_pending / memory_accept | 自动蒸馏候选区:查看 / 确认入正式记忆 |
memory_update / memory_archive / memory_rollback | 更新(supersede 保留历史)/ 归档 / 回滚 |
memory_expand | 通过 sessionQuery 展开 sourceSession/sourceSeqs 原始事件 |
memory_stats / memory_maintain | 统计 / 自动维护(去重、压缩索引、合并候选) |
核心特性:命名空间隔离(<memoryDir>/<namespace>/...,默认 workspace 目录 + git 分支)、自动蒸馏(turn/end 成功工具调用 → pending/,确认后才入正式记忆)、自动维护(maintainEveryTurns 默认 20)、渐进式工具暴露(progressive: false 可回退全局注册)。
核心公理:行动验证(No Execution, No Memory)、神圣不可删改(已验证事实可压缩迁移、严禁丢弃)、禁易变状态(时间戳/PID/临时路径不存)、最小充分指针(L1 只写存在性)。注入走 user-role 快照,不破坏 DSH 的 KV 缓存命中率(设计细节见插件 README)。
dsh-annotation-patched(选中批注/引用,fork 增强)
| 能力 | 说明 |
|---|---|
| 选中批注 | 选中助手回复文字 → 批注(可留空)→ 回车随消息发送;自己的气泡不显示批注块(零闪烁隐藏) |
| 逐条对照 | 模型按 Annotation 1: … 逐条回应,回复中为可悬停芯片(回看原文+批注) |
| Codex 式「引用」按钮(增强①) | 选中文字 → 工具栏「引用」按钮 → 回车即带(空批注纯引用),显式确认制,复制/阅读选中不会误触发 |
| 幽灵引用修复(增强②) | 拼稿即清待发送集(原版依赖装饰扫描轮询清理存在竞态残留) |
来源:omdsh-dev/dsh-annotation v1.3.13(MIT),全部改动带 PATCH(2026-08-14) 标记,详见目录内 README.md。
dsh-side-panel-patched(右侧工作区面板,fork 增强)
| 能力 | 说明 |
|---|---|
| 文件树 + 多文件 tab | 文件树点文件 → 独立 tab(同时打开多个文件,切换/单关/查重激活),树单例跟随激活 tab、滚动位置跨 tab 保持 |
| 会话跟踪 | 切换工作区 → 树重载当前工作区;文件 tab 按会话分组(各自保留、切换显示、互不串扰) |
| Git 审查 / 终端 | 工作区变更审查(stage/unstage);终端 Windows 友好降级(Unix PTY 限制不崩溃) |
| 布局增强 | 绕开官方 520px 宽度上限(420~60% 视口自由拖宽)、头部与官方 header 像素级对齐、Codex 风格梭形拖拽把手、放大按钮全宽切换 |
来源:ccq1/dsh-side-panel v0.2.0(BSD-3-Clause),全部改动带 PATCH(2026-08-14) 标记,详见目录内 README.md。
⚙️ 环境要求
| 使用场景 | 要求 |
|---|---|
| DSH 插件 | Node.js + DSH(@deepseek-ai/dsh-tools、@deepseek-ai/dsh-credentials) |
| dsh-vision-skill / vision-skill | 额外需要 Python 3 + Pillow,以及任意 OpenAI 兼容多模态模型 API Key(Qwen-VL / MiniMax-M3 / Gemini / GPT-4o,默认 MiniMax-M3) |
| 通用技能(vision / video / ppt / markitdown / automation) | Python 3.x + 各技能列出的 pip 依赖 |
| Hermes 插件 | Hermes 框架 |
❓ FAQ
Q:通用技能和 DSH 插件怎么选?
A:通用技能跨框架,任何 agent 都能挂载;DSH 插件是 DSH 原生扩展,走官方接缝(工具注册 / Credential / 上下文注入 / 布局插槽),能力更强但只适用于 DSH。两者能力互通——dsh-vision-skill 就是把 General_skills/vision-skill 包装成 DSH 原生插件。
Q:我的模型不支持图片,能识图吗?
A:能。直接贴图会被框架拒绝(MODEL_DOES_NOT_SUPPORT_IMAGES),改用两种方式:① 发图片的本地路径文本;② 截图后说"看图",vision_clipboard 自动保存到工作区再识别。这是纯文本模型的能力门禁,不是插件问题。
Q:视觉 API 用哪家?
A:任意 OpenAI 兼容的多模态模型接口,通过 VISION_API_URL / VISION_MODEL / VISION_API_KEY 注入,不写死任何厂商。
Q:子目录之间有关联吗? A:没有。每个子目录是独立的自包含单元,可单独使用、单独发布、单独删除。
🤝 贡献
- 每个子目录是独立的自包含单元,欢迎以 PR 提交新技能/插件,或提 Issue 反馈问题。
- 贡献要求:自包含(自带脚本/模板/文档)、许可证清晰(建议 MIT)、不写死密钥与本机绝对路径。
- 新增技能的入口文档统一为
SKILL.md,DSH 插件另附cordis.patch.yml与package.json。
📄 许可
本仓库全部内容以 MIT License 分发。社区来源内容保留原作者署名(见各子目录 SKILL.md / plugin.yaml 头部)。
Read the usage guide →
Install steps, key points, FAQ and compatibility for this plugin — auto-derived from indexed fields.
Listing badge
[](https://deepseek-plugin.org/plugins/DDDFXYqiming/Agent_Extensions/dsh-plugins/dsh-ocr1-memory)Paste this markdown into your GitHub README to link back to this listing. The badge only states the listing — not a security endorsement.