プラグイン

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.

Layered memory for AI agents: five verbs (wake/work/pit/tomb/close), core layer read every time, archive on demand. Plain markdown, four pages created on first run; survives restarts, model swaps and plugin removal.

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.

Restarts the DSH desktop host on macOS when a change needs it, then hands the conversation back to the same session with a note the model writes about why it restarted and what comes next.

Wall-clock session and turn timing for the DSH Web GUI: a timer chip in the session header shows the session total, every finished turn shows its own duration above the action row, and a sidebar panel totals today, the last 7 days, the last 30 days or all sessions. The numbers are folded from turn/start and turn/end in the session log, so paging, compaction and restarts do not change them.

Remembers the model used before quitting and restores it as the startup default.

Local LoRA and QLoRA fine-tuning in a panel: import JSONL, see a VRAM estimate before training starts, evaluate, and export an adapter. One-click Python venv setup, but you must supply your own Python 3.10+ and an NVIDIA GPU (6 GB or more). Verified end to end on Windows 11 with an RTX 3060 6 GB; the installer refuses non-Windows hosts, so Linux, macOS and other GPUs are unsupported for now.

Queues composer messages sent during DeepSeek peak billing hours and delivers them 3 s after the next off-peak window starts. A dock above the composer shows the countdown with send-now / edit / cancel, the queue survives closing the browser or restarting DSH, and attachments are staged on the host.

A countdown pill under the message composer showing how long is left before you clock off, with a workday progress bar; click it to set your own start and end times (saved in this browser), and after the end time it turns into an overtime timer.

Page-level startup splash: a Penrose triangle light sweep over a living isometric diamond ocean, where the frame itself is the progress gauge, paced by the intro but capped by real DSH boot milestones. Any bare key skips it, ten palettes come from Monument Valley and Geometric Islands, and when the intro ends the triangle stays on as a small mark beside the composer that reflects what the agent is doing.

First-paint splash for DSH: pushes a branded splash page into the boot HTML as an index-injection row, so the desktop window opens already showing the splash instead of a white/loading flash. Fades out and hands over once the startup-animation plugin starts (checked via `window.__DSH_STARTUP_RUNNING__`), with a 6-second fallback (configurable via `maxMs`) so it can never trap the app behind the splash. A normal dsh.bundle plugin: no host changes, no app.asar patching.

Plugin steward for DeepSeek-Harness: checks every installed plugin for newer versions and installs them, snapshots the profile first and rolls back automatically when the post-update health check regresses. Also scans plugin code for risky behaviour before you install (eval, reverse shell, credential access), browses the 8.5k-plugin catalog with compatibility badges, restarts the host by itself after install/uninstall/disable, and shows everything in plain language.

Sidebar plugin updates with publish dates: each update pins an exact version and re-reads the installed manifest to confirm it landed, and updates whose new code needs a full relaunch are counted on a restart button — whose replacement process is started through WMI so it inherits no console. The full relaunch is Windows desktop only; the in-page GUI reload works on any platform.

A settings page that edits the current project's CLAUDE.local.md, the private per-project instruction file DSH's built-in loader reads at the start of a session; the file stays out of git.

File-state cache skill for coding agents: one explore call replaces ls+grep+read, reads remember they already happened, and edits return a diff plus the exact changed line range instead of a full re-read. State is a JSON cache on disk, so it survives across tool calls and restarts. Requires Python 3.8+ (standard library only).

Registers the hosted SpecStream MCP server with the harness MCP manager and keeps the API key in the credential store. The server returns live web data as structured rows, each value with its source URL, and a run starts only after the quote's maximum is approved.

Connects DSH to timestamped video reading, shared queues/history and Scroll personal Bilibili workflows through an existing Video Reader installation. Windows x64 only: install the core and set VIDEO_READER_ROOT before starting DSH; the bundle does not install Python, FFmpeg, models or Bilibili credentials.

Restores the Windows desktop after a restart or power loss: snapshots open apps, documents, folders and window positions, and reopens them on demand. Windows 10+ only; automatic capture before shutdown needs two scheduled tasks registered once with collector/install-tasks.ps1.

Hippocampus: renders workspace files, DSH memories and past sessions as a rotatable neuron graph in the sidebar, with Chinese-friendly labels and automatic re-indexing on every start.

Lists every session stored in the local DSH profile with its title, workspace, last-modified time and size, then moves the selected ones to a 90-day trash you can restore or purge; deletion detaches the live session first, so the sidebar updates without restarting the app.

A self-hosted digital-life companion for DSH. Three slow-moving hormones (dopamine, cortisol, serotonin) set its mood and tone, a memory layer turns chats into events and facts with version chains and a forgetting curve, and it writes, hot-loads and unloads its own organs (tools) when a capability is missing. It handles text, images, stickers, voice notes with text to speech and speech recognition, and file uploads; the web space holds diary posts and guestbook comments, and it starts conversations on its own schedule. The built-in web server listens on 0.0.0.0:2332 by default, so create the owner account before exposing the port.

Two round buttons at the foot of the DSH desktop sidebar on Windows: restart the app without a console window ever flashing on screen, and open the DeepSeek top-up page in your browser. The restart path launches the helper through WMI and wscript so the new process never inherits a console; it verifies the executable path before killing anything and preserves the original command line. Windows 10/11 only (the package declares os: win32).

Adds a shared Sup composer switch on Windows to start or gracefully stop a separate Super-agent process and release its memory. Requires a working DSH NEXT install with Node 24+, the standalone DSH CLI and an already-configured independent Super-agent profile (verified on DSH 0.2.1-rc.4/rc.5); the bundled bridge.js must also be registered in the Super-agent profile — installing the desktop package alone does not complete setup.

Hide the duplicate DeepSeek account / official API entries, sidebar items and the Feedback / Sign out items; on DSH Desktop, add Reload / Restart to the application menu with a one-click patch to the app shell main.js (needs an app restart, and a DSH update reverts the patch); pin a reasoning level and auto-fill new providers and models.