yyh-001/dsh-meme
Chat meme stickers: text-only send, mood auto-send, QQ/WeChat-style picker, auto-learn, custom packs.
Install
via npm
Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.
The desktop app keeps its own profile, desktop, and only the dsh command it ships may change it — the npm-installed dsh refuses that profile. Install the command from the app menu (Manage dsh Command…), open Desktop once, quit it fully, run the line below, then reopen Desktop.
via npm
Resolves a published tarball rather than cloning the repository.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/desktop/pnpm-workspace.yaml.
Our install check ran in a web profile on npm's dsh, not in the desktop app.
What happened when we ran it
Installed cleanly when we ran it
Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 8d agoon DeepSeek Harness 0.2.2-rc.1.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
Security
No build script was blocked in our run.
Source: our sandbox install on DeepSeek Harness 0.2.2-rc.1, 8d ago.
package.json declares no preinstall, install or postinstall script.
Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.
shell commands (bash, exec, spawn …)
Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.
Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.
What it is — DeepSeek Harness plugin that lets you insert meme stickers one-click in chat and have the model generate images via text tags for continued battles, plus auto-learning for user-uploaded images.
Who it is for — When you want the model to keep generating visual replies in Web chat but its image input support is limited, this allows text-tag based image sending. Not suitable for pure text chat users, since it will actively insert images.
Watch out — Sandbox testing succeeded: installed in a fresh profile and registered by harness. Static check notes that it can execute shell commands. No obvious issues found.
The verdict — I would install it because it lets text-only models generate visual content in chats without native image support, but only if the user is willing to manage their own sticker packs.
Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.
dsh-meme is a DeepSeek Harness plugin that adds searchable, selectable and AI-triggered meme images to chats.
DeepSeek Harness loads dsh-meme with two tools: send_meme selects an image by tag or query, while learn_meme adds a recent or specified upload to a library. In Web chats, the model returns a text marker such as [表情: 描述], which the front end maps to an image. In IM chats connected through dsh-im, dsh-meme supplies an absolute image path for native image delivery instead. Libraries, captions and settings are stored locally; the default scan directory is ~/.dsh/meme-packs, and configuration is kept in ~/.dsh/dsh-expression.json. The built-in library uses Node's SQLite support.
dsh-meme is intended for agents where meme search, manual picking, custom packs or image learning are useful. It requires Node.js ≥ 22.13.0; automatic image recognition requires a model that accepts image input. The plugin is a poor fit when text-only replies are preferred, or when a chat does not use the Web marker flow or a supported dsh-im image-delivery path. The listed terminal-surface risk matters because dsh-meme reads and writes local profile and library files, and its documented maintenance workflow uses pnpm in the DeepSeek Harness profile. Its HTTP interface accepts only loopback addresses.
DeepSeek Harness stores dsh-meme settings in ~/.dsh/dsh-expression.json and scans ~/.dsh/meme-packs for user libraries by default. The settings panel can change the scan directory, enable AI-initiated sending, edit its prompt, and select the sending mode.
| Key | Values or default |
|---|---|
remoteDirUrl |
"" or auto for automatic sources; official for the official source; mirror for mirror sources; or a custom catalog.json URL |
| Sending mode | 自动 (default), 纯文字, or 图片 |
| AI sending | Enabled or disabled in the settings panel |
Installed libraries can be enabled independently. dsh-meme can import and export ZIP packs, install market packs, and verify release ZIPs with SHA-256.
DeepSeek Harness exposes these tools:
send_meme: use tag for a random image from an emotion bucket, or query for a description, keyword or filename. Results cover all enabled libraries. Supported tags are happy, angry, sad, shy, confused and daily.learn_meme: learn the most recent uploaded image by default, or specify attachmentId or imageUrl.The model should copy a returned [表情: 描述] marker unchanged in Web chat. GIF uploads are sampled into frames for recognition and remain animated in chat.
DeepSeek Harness requires Node.js ≥ 22.13.0 for dsh-meme. The plugin uses Node's built-in SQLite and has no third-party runtime dependency stated in the README. Through dsh-im, QQ, WeChat, Feishu and WeCom sessions receive native image messages; Web chat uses the marker-based rendering path.
Automatic learning needs an image-capable model. Animated WebP and APNG are currently identified from their first frame, while GIFs receive frame sampling. The HTTP interface accepts only localhost, 127.0.0.1 and [::1]; LAN addresses and custom domains are rejected. Market catalogues and previews are hosted on GitHub, although automatic mirrors and a local catalogue cache are available.
Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub
Same category
zhu1090093659
A whale-girl companion for the dsh web GUI: animations follow the agent state, with pat interactions and a feeding mechanic that raises intimacy from a calf to deep-sea bonds.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
PC2005-cloud
Desktop pet for the DSH Web UI on Windows, macOS and Linux: 106 transparent animations in the browser overlay or a transparent always-on-top desktop window, throw-and-bounce drag physics with squash and particle scoring, a work-status bubble driven by live session events, self-talk and chat with persistent memory, balance display, meme-image bubbles, multiple pets on screen, and drop-in custom animations and pet packs.
Installed cleanly when we ran it
flizzywine
Installs, updates, and switches to a separate DSH Tavern profile on official DeepSeek Harness Desktop for Windows and macOS. Forked from 2NF/dsh-profile-bridge (MIT); install this launcher or the upstream plugin, not both — they claim the same /profile-bridge channel.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
Nagi-ovo
Parody ads in 2005-Chinese-web style: sidebar banners, in-chat feeds, corner popups, and a close button whose hit area is smaller than it looks. All fictional.
Installed cleanly when we ran it
QCYTSN
Desktop-native BigFish companion for DeepSeek Harness — real Agent status, always on top on Windows.
Installed cleanly when we ran it
Alterssss
A Bilibili companion that keeps its own schedule. A 60-second tick in the plugin host wakes a dedicated agent session at a random moment inside the configured time windows (opting out of a day is a configurable chance), then hands it a bundled CLI of 38 subcommands — feed, subtitles, danmaku, comments, ffmpeg frame grabs, and two diaries. Shares at most N items a day by commenting on them and @-mentioning the owner (default 3, enforced from a written quota log, and it stops on rate-limit or captcha signals). Also polls comment replies, direct messages and live-room danmaku; replies to anyone but the owner are queued for approval in Settings. Settings → 养鱼 writes ~/.dsh/bili-whale.config.json; cookies live separately in ~/.bili-ai/credentials.json and are never echoed back. The HTTP routes are loopback-only behind DSH's trust fence. Needs Node 18+ and ffmpeg on PATH for frame extraction.
Installed cleanly when we ran it