A DeepSeek Harness meme plugin — pure-text `[表情: 描述]` tokens, two built-in libraries, `send_meme`/`learn_meme` tools, zero third-party deps (node:sqlite only).
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-30
License
MIT
01What can it help you accomplish?
Send and reply with memes through pure-text chat in DeepSeek Harness
Fetched meme images rendered in chat bubbles as `[表情: 描述]` text tokens — no image-input capability required
DSH chat / QQ- and WeChat-style bot users who want expressive meme replies
Let the model automatically learn and catalog new memes from user attachments
`learn_meme` records the most recent user attachment (no attachment id needed) and auto-detects category/description; also accepts a URL
Users who want to grow a personal meme library without manual tagging
Proactively send a meme that matches the conversation mood
Pick an emotion bucket, randomly draw several captions, and the model pastes one into the reply
Companion-style agents that should react emotionally rather than only answer text
02How to install into DeepSeek Harness
Prerequisites
- A DeepSeek Harness runtime with a target DSH profile to install into — the README installs into e.g. `~/.dsh/profiles/web/`
- Node.js with the built-in `node:sqlite` module — the only dependency, zero third-party deps
Installation steps
- 01
Install from npm into a DSH profile: `dsh plugin --profile web add dsh-meme` (equivalent to `pnpm add dsh-meme`)
$ dsh plugin --profile web add dsh-meme
- 02
Or install directly from GitHub / local: `pnpm add github:yyh-001/dsh-meme` or `pnpm add file:/path/to/dsh-meme`
- 03
Switch the active library in Settings → 当前图库 dropdown — built-in `official-001` works out of the box, no config needed
Verify the integration
Not specified by the author
03DSH integration and capability boundaries
Native DSH plugin — registered via `dsh plugin --profile web add dsh-meme`; exposes `send_meme`/`learn_meme` tools to the model and mounts a settings panel + 😊 picker through `cordis.patch.yml`, with dsh-companion providing the message channel.
Text-based meme sending (send_meme)
emotion tag (e.g. sad/happy) + optional limit→candidate `[表情: 描述]` tokens pasted into the reply; the frontend renders the matching image in the chat bubble
Auto meme learning (learn_meme)
optional attachmentId / imageUrl→records the most recent user attachment into the library and auto-detects category/description
Mood-driven proactive sending
emotion bucket (happy/angry/sad/shy/confused/daily)→random sample of captions from the bucket; the model picks one to paste into the reply
Library management & import/export
upload / edit / delete memes; ZIP file→persisted library with category management; one-click ZIP export/import of a meme pack
settings stored in `~/.dsh/dsh-expression.json`, survives plugin upgrades
04Who is it for? When not to use it?
Good for
- DSH chat / QQ- and WeChat-style bot users who want expressive meme replies
- Users who want to grow a personal meme library without manual tagging
- Companion-style agents that should react emotionally rather than only answer text
Not for
- `learn_meme` auto image-recognition depends on the current default model supporting image input; if unsupported, you must manually specify the tag/caption.
- The bundled `official-001` library's upstream provides NO LICENSE (no explicit redistribution permission); personal default use is fine, but public redistribution must keep the upstream source attribution in manifest.json.
05Compatibility, maintenance and safety notes
- `learn_meme` auto image-recognition depends on the current default model supporting image input; if unsupported, you must manually specify the tag/caption.
- On disk memes keep fine tags (angry/baka/…) but the model only sees six emotion buckets; when captions don't align, the frontend folds quotes before matching.
- The bundled `official-001` library's upstream provides NO LICENSE (no explicit redistribution permission); personal default use is fine, but public redistribution must keep the upstream source attribution in manifest.json.
MIT licensed · published to npm as `dsh-meme` · last push 2026-08-20 · no tagged release yet
06Frequently asked questions
How do I install dsh-meme into DeepSeek Harness?
Run `dsh plugin --profile web add dsh-meme` (equivalent to `pnpm add dsh-meme`) to install it into any DSH profile such as `~/.dsh/profiles/web/`. You can also install directly from GitHub with `pnpm add github:yyh-001/dsh-meme` or a local path.
What are the prerequisites?
You need a DeepSeek Harness runtime with a target DSH profile to install into, and Node.js with the built-in `node:sqlite` module — dsh-meme has zero third-party dependencies, so it's ready to use right after install.
How does dsh-meme connect to DeepSeek Harness?
It's a native DSH plugin: it registers `send_meme` and `learn_meme` tools the model can call, mounts a settings panel and 😊 floating picker via `cordis.patch.yml` (hot-mount, no restart), and pairs with dsh-companion for the message channel.
How is it different from a normal image bot?
The model never handles images — the UI displays the meme while only `[表情: 描述]` text tokens go through DSH, so it doesn't trigger DSH's image admittance checks. Six emotion buckets (happy/angry/sad/shy/confused/daily) drive selection instead of raw image input.
Troubleshooting: pnpm installed an old version?
pnpm enforces a 'new package safety window' (default 24h) and may silently fall back to an older version right after publish; add `dsh-meme` to `minimumReleaseAgeExclude` in `pnpm-workspace.yaml` if you need the latest immediately.
07Related DSH workflows
dsh-pet
by pc2005-cloud
DSH Web 界面桌面宠物：51 个透明 webm 动画随机链播、屏幕漫游、点击/拖拽；附提示词配方+AI 视频素材生成链可自造宠物
whale-girl
by vlln
DSH Web 桌面宠物（可拖拽/投喂/玩耍，积累型资历成长）
dsh-dafeiyu
by qcytsn
Desktop-native BigFish companion for DeepSeek Harness — real Agent status, always on top on Windows.
dsh-kun-like-pet
by liyupi
桌面宠物「小坤宠」：Web 界面右下角随 Agent 工作状态切换 9 种动画，任务完成播放「你干嘛~哎哟」音效；host 状态机 + client shell.overlay 渲染 + 拖动/点击互动。
08Data and sources
**dsh-meme**（原 `dsh-expression`）是 DeepSeek Harness 的表情包插件——找得到、发得出、学得会：
dsh plugin --profile web add dsh-meme
已发布到 **npm**（`dsh-meme`），一行装进任意 DSH profile（如 `~/.dsh/profiles/web/`）：
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-30. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.