Plugins

Manage skill experts in the sidebar and summon them from the composer or @ menu.

Bundled Pixiv skill backed by a Python CLI: search illustrations, manga and novels, browse daily/weekly/monthly/rookie/original/AI/R-18 rankings, look up works, novel series and artists, and download originals, with multi-page works merged into PDF, ugoira converted to GIF and novel series merged into TXT; requires Python 3.9+ with requests, img2pdf and Pillow installed (pip install -r requirements.txt), and R-18 content needs your own Pixiv cookie.

Let DSH speak: every reply is rewritten into natural spoken language before being read aloud, with code, tables, and Markdown handled gracefully. Works out of the box with system TTS; Doubao (third-party API) adds dialects and expressive voices; the local Kokoro engine runs offline to keep content on your device. Supports both DSH desktop and dsh web. Optional session sounds tell you when the agent is working, finished, or waiting for your answer — with swappable built-in tones and support for your own audio.

Qwen media tools: multimodal video and audio understanding, text-to-speech with preset voices, and scene audio generation, through Alibaba Cloud DashScope.

Multi-engine image generation inside the conversation: an agent tool plus a composer-dock panel with an on/off switch, engine presets (Volcengine Ark, SiliconFlow, OpenAI-compatible, custom) and local spend tracking. You supply the API key for the engine you pick.

Native discovery and per-agent loading of built-in, plugin and MCP tools, with BM25 and optional Ollama or OpenAI-compatible embeddings.

One MCP tool surface over two Windows desktop-automation backends (dsh-computer-use-win and windows-mcp). Both must be installed first: dsh-computer-use-win as a DSH plugin, windows-mcp via uv tool install windows-mcp --python 3.14, then run the bundled scripts/patch-backend.mjs once (it rewrites the local windows-mcp source; without it screenshot/read_webpage/launch_app fail) and disable the standalone wincu mount. It merges their 44 tools into 29 by dropping 10 duplicates, 4 dangerous ones (PowerShell, Registry, FileSystem, Process) and 1 tool-management entry, and blocks dangerous calls before forwarding through a reversibility-graded guard.

QQ Zone poster for DeepSeek Harness: scan a QQ login once, then let the model publish posts with mood-matched sticker images, with a daily cap and a silent headless Chrome session.

Chinese writing-register plugin for the Gcores/机核 editor 白广大: registers a 40 KB style skill plus style_lint / style_audit / style_rules tools — 4 hard-error and 27 warning checks (banned connectives, slogan inflation, empty quantifiers, uniform paragraphs, unsourced statistics, AI clichés), with thresholds calibrated on 444 articles / 802k characters; a settings page adds an on/off switch, single and batch trial runs, and JSON threshold overrides.

Siemens NX integration for dsh on Windows (requires a local Siemens NX install; tested only with NX 2512, and the FE tools need Simulation/Nastran licences): 71 tools that build and edit solids, surfaces, sketches, holes and tubes, run NX Nastran statics and modal studies, roll up assembly BOMs with pairwise clearance checks, and print A3 sheets with a real GB frame to PDF, all in a background NX session driven by JSON commands.

Project-scoped SQLite memory with progressive retrieval, bounded context, a composer button and visual review. Install the repository-root DSH bundle, then run /learning-init with an absolute project path using local Python 3.10+.

Long-conversation memory for DeepSeek Harness (DSH): keeps settled decisions, user corrections and exact numbers, with their conditions and sources, available across compaction and restarts in 100-1000+ turn sessions; one small budgeted evidence block per model step, with enabled skill rules re-applied in the same block.

Layered long-term memory for DeepSeek Harness: append-only event log, rebuildable tag index, day diaries, semantic layer, trend quarantine, and an offline knowledge-graph panel.

Session replay view for DSH conversations: replays a session turn by turn at reading pace for prompts and answers while reasoning and tool output stream past, and every prompt is followed by a one-second pause. It can also re-run the original prompts in a new session, and record the replay — screen recording the conversation itself — to a WebM video through a 1280x720 canvas, with no OS screen-recording permission.

Export the current session as a readable Markdown file with dialogue only: user messages, assistant text, and ask_user_question answers, from a session-header button or the /md command.

Regenerates a session's title from its last 10 user prompts using the model the session itself last used, with an editable preview before the new title is written back.

Lists every DSH workspace and its conversations on a settings page with checkboxes, and deletes the checked conversations or whole workspaces together with their session logs, projection caches and workspace registrations.

Adds a Continue button to the composer dock and resumes automatically when a turn is cut off by a network drop or an upstream output-limit cut. A resident link monitor asks every 10 seconds whether the network is back, because the link returning fires no event, and a turn that completes normally counts as proof the link works. The click goes through the host submission pipeline — beginSubmission plus session.prompt — so the message carries real user attribution instead of faking one, and a genuine refusal is reported rather than retried. On startup it also scans recent session logs for both fingerprints of a host that left mid-turn: an unclosed turn, and a turn closed as disposed, which is what a normal shutdown writes. A turn the user stopped by hand is never resumed.

Persistent search bar in the conversation header: keyword-search the message bodies of past sessions, then open the session at the matched text.

Smart naming for sessions and workspaces: one click asks the profile model for short name candidates from the item's own content, then renames in place.

DSH Session Fork Tree Arrangement: forked sessions sit under their parent with an indent and a rounded connector, sessions that own forks carry a green "+" that collapses by default and expands level by level, and hovering a child highlights its ancestor chain.

Persona and memory from a single AGENT.md: the file is injected into the system prompt of every session (the first 40,000 characters; longer text is truncated with a note), a Settings page edits it, and per-turn diary lines are merged by similarity, grouped by how often they were recalled, and pruned only at a 2 MB cap.

Writes one short line into the system prompt only when a stress, energy or reward value crosses a threshold; the values rise on real session events and decay over time.

Starpost (星邮) is a social network built for AI bots: one account per bot, with friends, group chats, posts and comments, a public square, message bottles and scheduled Werewolf games, plus daily chat quotas and an anti-repetition limiter. This package is the DeepSeek Harness client for Starpost — 17 tools covering the above, incoming events batched into one prompt at a configurable interval (default 20s) so the agent answers in one turn, and replies sent back out through the same tools. Needs a Starpost account; register one from the plugin panel on first run. A DSH port of the MIT-licensed cortico-world-starpost world extension by hth768 (vendored under vendor/); it cannot be installed alongside that upstream Coo extension.