플러그인

Hold Alt (default; rebindable in the plugin page) to dictate and insert a cleaned-up transcript, plus a sparkle button that rewrites the composer draft into a clearer prompt. Dictation requires the Harness Voice Input plugin with its SenseVoice model enabled.

Windows-only sidebar panel that watches the CPU and IO of your AI desktop apps' process trees and shuts the machine down once all of them have been idle for a configurable time, with a cancellable countdown, a dry-run mode and an activity log; requires Python 3.10+.

Windows desktop control for DeepSeek Harness: accessibility-tree snapshots, click by control name, delivery verdicts, and repeatable task files.

Resumable multi-connection downloader with China mirror and proxy presets, plus DeepSeek-assisted resource discovery.

Resident multi-connection download engine for DeepSeek Harness: five rdm_* agent tools plus a sidebar download panel, with resumable, SHA-256-verified and bandwidth-limited transfers that survive a kernel or DSH restart.

DSH plugin: three MCP tool servers for DingTalk (via the dws CLI), Feishu (via lark-cli) and Feishu Project (via the official @lark-project/mcp), reusing the accounts dws and lark-cli are already logged in with, plus a Feishu Project MCP user token you paste in the panel; once the three connectors are connected, the default set is 140 tools (47 DingTalk, 45 Feishu, 48 Feishu Project) under the mcp__dingtalk__ / mcp__feishu__ / mcp__meego__ prefixes. A sidebar panel adds a connector wall with one-click connect (installs the CLI and walks through device-code login, or takes the Feishu Project token), custom MCP connections pasted as mcpServers JSON, enable/disable per connection, the write-tool switch, and a searchable catalog of the 1098 dws and 246 lark-cli commands.

Local-first resume warehouse for DeepSeek Harness: package your work into reusable bullets, import an existing resume into a template, analyse a job description (including the school-tier preference it implies), assemble a tailored Chinese or English resume and export a PDF named position-name-school. The whole app ships inside the npm package — server/, web/, skills/, scripts/, requirements.txt, no git clone needed — and one tool starts, stops and health-checks it; the first start installs the dependencies into app/.venv. Needs Python 3.10+ and macOS or Linux (bash). Nothing leaves the machine except the LLM calls you confirm.

Fusion 360 for DSH: bridges the MCP server Fusion ships (read, execute, update, electronics) with every upstream schema kept byte-for-byte while the always-on tool surface drops 70 percent, adds an editable endpoint under Settings, and wraps a local hf.py modelling loop as nine hf_* tools (needs Python 3.10+ and a fusion-harness workspace).

Runs Hindsight long-term memory on your own machine: after a one-time uvx --from hindsight-embed@latest hindsight-embed profile create server setup (~450 MB of Python dependencies) and with your own LLM key, the plugin manages the local memory server itself (health probe, start, stop, logs), registers ten hindsight_local_* tools for status, page search, page read, recall, remember and reflect, injects a knowledge-page index once per session, writes each finished turn back into the bank, and extracts facts with your own LLM key. Do not enable it alongside the official @vectorize-io/hindsight-coding-agents plugin: both read the same bank and would inject duplicate context. At session end it writes a handoff snapshot that the next session injects as previous progress. The data directory is configurable (dataDir) and scripts/relocate.mjs moves an existing install to another drive, creating directory junctions where the server hard-codes its paths.

Read-only persona injection for DSH: when a session opens inside your workspace, your persona files and the latest diary entries are prepended to the system prompt, and those source files are never modified. It keeps a short cross-session feed of recent messages under <root>/live/feed.json and can write a QQ hand-off file at <root>/live/web-for-qq.md; nothing is uploaded. Variable blocks (clock, recent actions, other sessions) are delivered as a per-step context message, so the prompt prefix stays byte-stable and keeps its cache.

One-off btw side questions that inherit the current DSH session, with selectable context ranges and an optional compressed summary you review before sending it into the main session.

Share a DSH conversation without making the recipient install anything — copy a 24-hour LAN link, export a self-contained web page they can open offline, or import a .dshchat file as a real resumable session when both sides run the plugin.

Injects your own text into the DeepSeek Harness system prompt as real system sections from a sidebar editor: each section lands after the persona, after the tool docs, or at the very end of the prompt, can be switched on or off, and can resolve {{variables}}; a preview runs the host's own assemble and render pass so you see the exact prompt the next request will send, with empty, duplicate, unknown-variable and oversize sections flagged.

Adds MiniMax open-platform models to the DSH model picker: paste the API key in Settings and MiniMax models become selectable, with the M Plan quota windows shown beside the composer.

Signs in to ima.qq.com (Tencent IMA) with a WeChat QR code and runs a localhost OpenAI-compatible relay in front of its SSE chat endpoint, so the four models behind it appear in the picker.

Global cyber-terminal theme: a click-through full-screen Matrix code-rain overlay, phosphor-green UI styling, a sidebar one-click toggle, and adjustable speed, density, opacity and glow with three palettes.

Drag the two handles to resize and move the DSH chat area as a floating window; position and size persist across reloads, and movement is clamped to the conversation pane so it never leaves the screen.

Right-click any selected assistant reply and add it to the composer as a removable quote chip. The selected text is delivered to the model as hidden context, so your message bubble keeps only your own words.

A DSH workbench for picking photos from local folders on macOS and Windows: local dedupe, filtering and grouping, AI grid triage and scoring with an image-capable model you supply (the plugin bundles no model, credentials or quota), then human review, calibration and export.

Keep pinned conversations from every workspace at the top of the sidebar, with drag insertion hints, manual or recent-first sorting, and completion-unread dots. Includes Codex-style row actions: a live spinning indicator while a session runs, archive and restore, inline rename that selects the whole title, and a right-click menu for fork and reordering. A magnifier beside the Global pins heading opens a search overlay: it matches session titles and workspace names instantly, then searches message content through the Host index when the deployment enables it, splitting results under small Sessions and Content headings with snippets.

MCP server panel for the DeepSeek Harness Web GUI: the sidebar lists every @deepseek-ai/dsh-mcp-client row — including rows inserted by other plugins — with a connection state derived from the loader fiber plus the mcp__<server>__* tool count, shows that row's configuration, enables or disables it by editing only that row of the patch file, and reconnects once after a failed attempt.

A collapsible column beside the conversation that organises conversations into a workspace/topic tree, opens the real sessions in place, and exposes the tree to the assistant through 9 model tools.

Open delivered files, changed-file rows and inline file mentions in the system default app with a left click; right-click takeover is configurable: all menus, only where DSH has none, or never. Desktop app only: the Web client has no system-open capability, so clicks stay with DSH.

An enhanced fork of PC2005-cloud/dsh-pet (do not install it alongside the upstream dsh-pet): a desktop pet for DSH with schedule reminders, approval and question bubbles you can answer in place, a 20-entry history ledger, double-click corner cycling, a configurable data directory, a step/elapsed progress line, snooze and one-hour mute, a right-click menu whose order and hidden items you can edit in settings (chat first by default), and a task-queue progress bar inside the work bubble.