Deployment-level static web plugin for DSH: cerrda dark re-theme of the DeepSeek Harness Web GUI (rose/purple oklch, Liquid Glass composer, Silk WebGL2 background, Sora/Fraunces/JetBrains Mono). Install with: dsh plugin --profile web add dsh-cerrda-theme
Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Cerrda/dsh-cerrda-theme
Legacy-compatible DSH plugin: a Codex-style per-turn git working-tree change summary bar above the composer, built for DSH Desktop 2.0.13 / DeepSeek Harness 0.1.5-rc.2
Interface extensions · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kahomesl/dsh-chat-diff-summary-legacy
Chat flow layout plugin for the DeepSeek Harness web UI: settled tool calls, context injections and finished reasoning pile horizontally as compact chips.
Abstract interaction layer between DeepSeek Harness (DSH) and IM platforms (Feishu, WeCom, ...). Channel-agnostic hub with proven interaction patterns (dedupe, instant ack, wait-reply, followup wakeup, scoring-based model routing, approval gate) plus pluggable adapters for Feishu and WeCom.
Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kovey/dsh-chat-interaction
DeepSeek Harness plugin: a DeepSeek-web-style conversation rail on the right edge of the chat column — one dash per human message that expands into a jump list on hover
Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Stellight/dsh-chat-rail
Widen the DeepSeek Harness Web UI conversation content area (shipped default 748px) by overriding the chat-width CSS variables; configurable via the plugin row config.
Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:garrisonz/dsh-chat-widener
Fold and expand the dsh web chat window automatically: event-cycle checkpoints (every 25 session events, from N=75) fold older loaded pages beyond the recent 50 rows when the viewport sits at the bottom; scrolling to the very top appends up to 50 earlier messages with the viewport kept in place, repeated until no more history. Per-session isolated; window stays below ~75 rows (low-end friendly); system "Load earlier" button hidden; configurable via row config (foldThreshold=50, foldCheckEvery=25). A DSH web profile bundle.
Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dove-a/dsh-chat-window-fold
DeepSeek Harness (dsh) plugin that checks whether the installed @deepseek-ai/dsh is the latest npm release and shows a native-looking, centered upgrade dialog in the Web UI. Linux / macOS / Windows, zh / en following the configured DSH language.
A pixel chicken desktop pet for DeepSeek Harness: it naps, paces, pecks, ruffles its feathers and spins a basketball on its own, and reacts to your agent's work
Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lizhuangCoding/dsh-chicken-pet
Desktop signal plugin for dsh: ring a chime when a task finishes, waits for your approval, or runs into an error — without keeping an eye on the terminal.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JohnXu22786/notifier
Find the right plugin, then get started
Search by task
Use a feature keyword or category, then sort by recent updates or GitHub stars.
Explore capabilities
Read the description, AI analysis and original README to understand what a plugin does.
Check and install
Review compatibility, dependency ranges and instructions, then copy the available install command.
Questions about DSH Hub
What is DSH Hub?
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
Does inclusion mean a plugin is tested and compatible?
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
How do I install a plugin?
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.