Plugins
Browse, filter, and install DeepSeek-Harness plugins.
8607 plugins found
dsh-pet-ai-sisters
linyucion/dsh-pet-ai-sisters
Chibi desk-pet pack for `dsh-pet`: ships 16 AI-model personas, each with 17 transparent 24 fps VP9 WebM animations (272 clips total), 4 reaction PNG stickers (64 total), an avatar and a preset config. On enable, syncs the selected `pets` roster (`all`, `wave1`, `wave2` or a comma-separated list) into `$DSH_HOME/dsh-pet/pet/` (fetching four SHA-512-verified `@linyucion/dsh-pet-ai-sisters-pack-*` tarballs from npmmirror / npmjs in the background when installed from the lightweight npm bundle) with a `.ai-sisters-manifest.json` version stamp while preserving user-modified `display`, `size`, `position` and toggle fields in `<id>-config.json`, then calls `/dsh-pet-7340/reload`. Registers five right-click menu actions via `/dsh-pet-7340/menu/item` — foreground-window top perch (Win32 `GetForegroundWindow` bounds on Windows, fixed fallback elsewhere), two-pet paired-line skit, folder peek, screen-glass knock and cloud nap — and unregisters them when disabled.
dsh-better-workspaces
ds-hu/dsh-better-workspaces
Worktrees, diffs, pull requests, and issue references inside the DeepSeek Harness Web GUI — now delivered as four independently switchable feature plugins.
dsh-connect-madao
xlnc-l/dsh-connect-madao
Brings Huawei Cloud CodeArts Agent models into DeepSeek Harness — 12 models including GLM-5.2, GLM-5.3, DeepSeek-V4.1 and Kimi-K3, with image input, tool calls, thinking levels and a daily check-in button. Speaks the gateway's signed and SM4-GCM encrypted protocol directly; the CodeArts desktop client does not need to run.
dsh-remote-dc
lonelycrab888/dsh-remote-dc
Integrates Desktop Commander Remote MCP with DeepSeek Harness to browse files, search logs, and run commands on paired machines without a public IP, inbound ports, or SSH.
dsh-connect-doubaowork
joseph2young/dsh-connect-doubaowork
Runs a loopback OpenAI-compatible gateway that routes DeepSeek Harness model requests to Doubao work mode, exposing Doubao, DeepSeek, Kimi and GLM models with streaming replies.
DSHGuard (dsh-guard)
gluztm/dshguard
Cross-platform DSH Web sidebar & CLI manager: plugin/MCP switches, symlink repair, one-way .credentials.yaml key setup, config snapshots with SHA-256 rollback, and desktop coordination.
dsh-theme-studio
ruohan0713/dsh-theme-studio
Twenty original literary themes for the DSH Web GUI: each ships light and dark palettes, 116 design tokens and an animated wallpaper. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-progress
himleoing/dsh-progress
Code can Vibe, progress must be Visible. No guess, less stress. See progress you can assess. Make project progress visible with local algorithms, optional AI assistance, task checklists, and subagent tracking. View overall progress, subagent activity, current operations, and estimated time remaining in a draggable panel. Supports DeepSeek Harness Web and Desktop. Requires Harness ≥0.2.2-rc.1 and Node.js ≥24.9.0. Local estimates require no additional model requests. AI assistance is off by default; enabling it incurs charges from the selected model provider. Probe usage and estimated costs are available in the panel.
dsh-plugin-telleru
kookoolive/dsh-plugin-telleru
Type /telleru in any conversation and an AI tutor teaches it on a whiteboard in the right sidebar: it clarifies your goal, checks your level with quick questions, has you confirm an outline, then writes structured board content (tables, flowcharts, formulas, code) step by step with optional voice, subtitles, quizzes and interruptible Q&A.
dsh-workspace-ide
echovic/dsh-workspace-ide
A VS Code-like workspace panel with a JetBrains-inspired editor: lazy file tree, TypeScript code viewer with syntax highlighting, soft-wrap, find & replace, Quick Open, multi-tab drafts, bracket matching/auto-pair, workspace-wide text search, git status/history with coloured diffs, six VS Code palettes plus follow-DSH, Markdown and image/SVG previews. Nine authenticated host routes serve the filesystem, images, git reads and a quick-open file index.
dsh-qualityforge
lpeixin/dsh-qualityforge
A QA plugin for DeepSeek Harness that runs end-to-end checks on a project (build, typecheck, lint, tests, coverage, dependency audit, secret scan) and writes a tickable report with P0–P3 severities and quality gates; execution is limited to preset commands and probing to loopback addresses.
dsh-memory-nebula
hanhan9999999999999999999/dsh-memory-nebula
Local-first memory nebula for DeepSeek Harness with graph views, evidence chains, hygiene checks, and offline snapshots. Reads the memory stores of every workspace and of other memory plugins (read-only, for example meow-memory's SQLite) and writes only under $DSH_HOME/memory-nebula. Registers 9 agent tools and a system-prompt section (usage rules every turn, plus not-yet-read neighbouring memories after a few reads); its /export and /share endpoints return the full memory text without authentication on the local server, and an optional standalone engine listens on 127.0.0.1:7890.
dsh-subagent-bridge
dogtiti/dsh-subagent-bridge
Subagent bridge: lets Codex delegate a task to DeepSeek Harness the way it would spawn a subagent (one call, waits for the answer), plus a codex_dispatch tool for the reverse direction.
agent-immune
meat-daemon-404/agent-immune
Self-evolving pitfall immunity for coding agents (Claude Code, Codex, Cursor, ZCode, DSH): capture failed-then-fixed tool episodes as SQLite+FTS5 antibodies and inject them before the agent repeats the mistake. Zero runtime dependencies.
dsh-compaction-tower
afeygu/dsh-compaction-tower
Automatic context compaction: a background observer distills early history into summary blocks, and when usage crosses the trigger line the engine commits whole blocks until it is back under the target line, with no model call on the commit path. Blocks merge into higher tiers as material runs out, and decompress or search_context reads any block back at its original length. The background observer spends model tokens: it uses the session's provider and model unless you pick another, with up to 10 distillations at once by default.
dsh-thu-automad
aaabrli/dsh-thu-automad
Tsinghua MadModel provider for DSH: renews the campus token automatically, switches between campus direct access and WebVPN, and serves model requests through a loopback transport with per-model queuing.
dsh-opencode-go-usage-badge
panther-w/dsh-opencode-go-usage-badge
One-line sidebar badge for OpenCode Go quota (5-hour, weekly and monthly windows), switching to the DeepSeek official balance when that model source is selected. Read-only, no telemetry. The OpenCode Go quota needs OPENCODE_GO_API_KEY configured in DSH, or an OpenCode Console login (its local credential file is read as a fallback), and the DeepSeek balance needs DEEPSEEK_API_KEY configured in DSH.
dsh-system-prompt-studio
user-mrz/dsh-system-prompt-studio
Per-conversation system prompt studio for DeepSeek Harness. Append text, shadow-replace one named first-party prompt section, or replace the whole system prompt; changes apply on the next model request without a restart. Overrides persist per session and are inherited by forked conversations along the parent chain, with a Pin action to freeze the inherited result locally. The panel lists the real assembled sections and guards unsaved edits.
dsh-approval-reason-dock
fzqxdedafeiyu/dsh-approval-reason-dock
Add an optional rejection reason to approval prompts: the text is steered into the running turn before the rejection is answered, and the panel only follows the session you are currently viewing.
dsh-bagu
hongdougao111/dsh-bagu
Two gates for outbound AI text. (1) Guard: before any text goes out it blocks the shapes anyone could write — padding verbs plus abstract nouns ("optimised the code structure"), hollow adjectives, universal filler, template openers, git commit/PR/review boilerplate, comments that narrate the code. Covers chat, comments, email, commit messages, PR descriptions, reviews, issues, docs and code comments. Passes with OK, blocks with one line naming what to change. (2) Catch memes: when someone drops a slang term the model does not guess or look it up — it already knows. A built-in 6792-entry meme wiki is queried before the model starts thinking, and the entry usage field ("how to answer this") goes straight into context. Matches only exact title/slug/alias hits, never fuzzy, so ordinary chat never triggers it. Bundled SQLite by node:sqlite, zero dependencies. Settings page: guard on/off, strict mode, prompt section toggle, meme wiki toggle, per-turn auto-lookup, a four-step tone slider (reserved / measured / follow the room / unrestrained) that is behavioural rather than a label, AI-completion switch (off by default, uses the session own model so no API key needed), a paste-and-test box, and three thresholds. No model call for any check. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-workspace-session-drag
liangzz1998/dsh-workspace-session-drag
Moves a session from one workspace to another by dragging it in the sidebar: a confirmation dialog first, subagent sessions travel with the parent, the list auto-scrolls at its edges, and an open idle session takes the move immediately through a registry refresh; moving into or out of the ungrouped group works both ways.
dsh-hippocampus
kianajunjie/dsh-hippocampus
Event-based memory for long-lived chat bots: emotion-weighted decay, three confidence levels on recall, superseding outdated facts, per-subject isolation, plus relationship, fact, chapter, skill and gap tables. Ships a CLI, an HTTP endpoint and a DSH plugin bundle.
dsh-plugin-toolkit
wjddidi-1/dsh-plugin-toolkit
Preflight for plugin authors: the checks the market runs — root export, dsh.client against exports\["./client"], whether npm pack ships the panel — on any folder or GitHub repo, from a panel or one command; plus release tooling and a Node testkit for client bundles.
zgs-ppt
john-20260101/zgs-ppt
Deck-generation skill for the National College Student Career Planning Competition. It takes a contestant's profile, materials and photographs, drafts a page-by-page outline for confirmation, then renders a 15-20 page reading-type PPTX (under 15 pages is flagged as a page-count error) using 17 page types, three built-in themes or a user-supplied template; the build audits the estimated layout (text overflow, per-page word count, missing evaluation dimensions, material gaps) and the rendered PDF is checked again for out-of-bounds and overlapping text. Requires Python 3.9+ with python-pptx, python-docx and Pillow; LibreOffice (soffice) and pdftotext are optional for the PDF layout re-check.