Plugins

Knowledge collection board for DeepSeek Harness: file chat answers, papers and notes into per-mode boards (study, academic, daily), browse them as a grouped kanban, timeline or calendar, link cards to each other, and roam a per-mode star map; ships an agent tool for adding and linking cards and scheduled collection tasks.

Tool-use visibility for dsh: an act wrapper and guard make every ordinary tool call carry a describe field (direct calls are rejected by default), the model narrates decisions in plain text, and live act cards with thinking, purpose, status and result show in a strip under the composer and, with the optional dsh-better-sidebar plugin, in a right-side digest panel. Also adds a background event tool for long tasks.

Companion for the DSH plugin market: batch-updates every installed npm plugin after DSH quits and relaunches it, rolls back the plugins an update broke when the next boot fails, and checks updates plus keeps snapshots for local link plugins. Windows DSH Desktop only; it is a companion patch for the plugin market (dshmarket), not a replacement — install dshmarket for the market tab.

Skill that deploys a folder to a public HTTPS address on Back4app with the Back4app CLI, on a temporary account with a claim link to keep the web app.

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, 1.6ms per query. 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.

QQ hub for DeepSeek Harness: private and group chats over OneBot v11 (SnowLuma/NapCat), with per-chat scoped memory, per-chat persona routing, a vision helper that narrates images for text-only models, multi-platform link parsing (large videos sent as group files, image galleries sent inline or as merged-forward messages) and a web panel for models, personas and settings. Derived from aureth-labs/dsh-aurabot-qq; do not install both.

Sessivra: drag sessions into resizable split views, insert native @ references into drafts, exchange linked replies and review delegated work before queued follow-ups. npm package dsh-plugin-sessivra.

DSH plugin: smooths running-turn thinking and tool output across all Work details modes, with a capped following window in Compact/Standard and row-level pacing in Detailed/Verbose.

Connects Tencent CodeBuddy CLI to DeepSeek Harness through ACP, with native CLI tool execution, multi-account management, and a standalone codebuddy_ask tool.

JetBrains-style IDE workbench in the DSH sidebar: Project file tree, Commit panel, Git history with a swimlane graph, a real PTY terminal and an embedded editor with Markdown preview and Find in Files, plus chat file links and send-to-chat references.

Adds a versioned DPIA workbench to DeepSeek Harness for source-linked facts, follow-up answers, reassessment, and reviewable reports. Needs Python 3.9+ with `python-docx`, `pypdf`, and (for PDF templates) `reportlab` + `pdftoppm`.

An Everforest colour theme for DeepSeek Harness, for both web and desktop. Forest tones, with six dark and light palettes. Chat content (headings, code, links, tables and more) is restyled with independent colours, and every tone and saturation level is tuned individually for a warm, gentle, easy-on-the-eyes experience.

Ollama Cloud provider for DeepSeek Harness: adds the chat route on install, publishes each model's own thinking levels for the composer effort control, keeps the model list current from the endpoint (/api/tags and /api/show, cached for offline boots), reads the account allowance from /api/balance into the Models page and a sidebar row that hides itself when the endpoint reports none, and offers Ollama's web search and fetch as selectable DSH web providers.

Bring your own wallpaper: import a local picture and its glass and ink are solved on the spot; plus twelve built-in full-screen wallpapers whose edge blur, feathering and glass opacity are computed per image; ink solved in OKLCH to hold WCAG AA; Rhodes Island iconography; approval and question cards signed with operator autographs.

Gaokao countdown blackboard: counts down the days to the gaokao on a desktop blackboard widget that collapses into a slim bar on double-click, and quizzes random knowledge cards while the agent works; open Markdown knowledge-card framework — drop .md files under subject/category folders and they load automatically, with cross-links, favorites, priority subjects and importing your own knowledge base.

Writes the harness agent live state (thinking, working, waiting, done, error) to a state file that a bundled Electron Live2D desktop pet polls, so the pet bubble and face follow what the agent is doing.

Auto-expands streaming thinking: always keeps the latest thinking block expanded, manual actions take priority, only the last block expands when opening a session, and nothing remains after uninstall.

dsh-ecolink DSH 适配层:直读本地记忆池、pre-step 注入(打分+预算+会话去重)、#记忆名 过滤,打通网页端记忆生态

Keeps a pool of models and routes every agent step to one of them with its reasoning effort set — configured by clicking in the composer, no JSON needed. The router takes over the composer's model cell, so one control shows the session's model and reasoning effort alongside the router's own settings. Three authorization scopes (model / effort / full) where a manual pick only counts in the scope that owns it, and in effort scope the router is bound to the one model you choose. Task presets with per-model weights, vision routing for image steps, session signals (active todo, context pressure, token budget, subagent depth), and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a thinking-enabled request whose history contains a tool call made with thinking off.

OpenCode Go subscription chat for DSH with per-model Completions, Responses, or Anthropic protocol selection, model discovery, context, vision and thinking metadata, effort defaults, and usage meters.

Universal skill adapter that registers any GitHub repo containing a SKILL.md as a DSH skill by cloning and symlinking into the official skills root.

Instance manager for DSH Web: a Mini Utility Dock panel that lists every local dsh web instance the machine can see (port, PID, uptime, live session count, resident memory, version), starts a new instance on an automatically picked free port in 3080-3129 or on a port you name, opens a row in a new tab, and stops one or all of them through that instance’s own graceful shutdown (appExit). Rows also show what each instance is serving, and read-only instance logs and session summaries are one click away. Where a peer is configured, the same panel lists and queries instances on other machines over a bearer-authenticated link. Every route is loopback-guarded, and a browser-facing action must additionally pass the host’s own browser authentication.

Bridges WeChat (ilink bot) private chats into DSH agent sessions and streams replies back, with hot-plug and a Settings tab.