LiangShen (梁神) agent preset for the dsh web GUI: a two-phase anchored-standard preset — the first model request exposes only the builtin Minimal exact two-tool surface (persistent bash plus str_replace_editor) with no runtime contexts or injected instructions (Minimal-aligned trajectory anchor), promotion is gated on the first minimal-like reasoning block with a fallback, and the wire then switches to Code Mode (PTC, a single run_code tool over the full registry) with the ordinary injections returning afterwards. The preset files are synced into ~/.dsh/.agent-presets on host startup. Hot-pluggable — mounted via cordis.patch.yml + a profile node_modules symlink, no dsh source changes.
Remote SSH operations for the dsh web GUI: host config store (~/.dsh/dsh-ssh.json, import from ~/.ssh/config), a persistent ssh2 connection pool with jump-host support, exec / PTY web terminal / SFTP transfer / local port-forward tunnels / cluster execution, plus agent tools (ssh_list, ssh_exec, ssh_upload, ssh_download, ssh_tunnel, ssh_cluster). Hot-pluggable — mounted via ~/.dsh/cordis.patch.yml + a profile node_modules symlink, no dsh source changes.
Answer hard questions with a one-page HTML: the model writes a short Markdown draft; the bundled CLI handles templates, SVG auto-layout and an STE controlled-writing check.
Skills · Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:QingYunA/answer-me-with-html
MemSearch plugin for DeepSeek Harness: shared markdown memory across agents, with capture, pre-step context injection, memory-recall skill, and a skill-candidate review panel.
AgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI
Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:NanmiCoder/dsh-agent-teams
DSH web plugin: a VSCode-like right sidebar (explorer / editor / terminal / git / browser), isolated per conversation session. Exposes a service for other plugins to register sidebar tabs and file viewers.
Wallpaper Engine backgrounds for the DSH web GUI: render your local Wallpaper Engine wallpapers behind the chat — Scene and Web in real time through the bundled WebWallGL engine, Video played directly — with iOS-style liquid glass, adjustable blur/scrim/border/opacity, custom typography and caret, and a liquid-glass makeover of the whole settings window. Prerequisite: DeepSeek Harness kernel >= 0.1.5 (0.1.5-rc.1+ — the official desktop line and DSH Desktop >= 2.0.7 both qualify). No version restriction on dsh-better-sidebar.
Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:elysia395/dsh-wallpaper-engine
TongFlow studio plugin for DeepSeek Harness (dsh): agent-designed project folders, one TongFlow workflow per generated asset stored next to its outputs, deterministic media generation, embedded canvas.
Agent collaboration · Vision tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tong-io/tongflow#8d47404f5b4c0027351f0af6ad607aaeeeef7ab2&path:packages/dsh-tongflow
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.