Plugins

Manage which models appear in the composer model menu. A settings page lists every provider's models with a per-model switch, provider-level show/hide, collapsible groups and filters by kind; switched-off models leave the menu while the model in use in the current session stays. The list can be searched by name or ID and filtered by capability (multimodal, reasoning) and by minimum context window (128K / 256K / 512K / 1M). Rows show the model kind, and chat models also show reasoning support with the adapter's effort levels, their context window and input modalities. Labels merge manual overrides, the settings document, the adapter, the relay's GET /models response, a built-in pi-ai / models.dev catalog, name inference and vendor corrections in that priority order, with the source named on hover and dashed borders marking inferred values. Any model can be edited by hand (kind, context window, modalities, effort levels); those edits are stored outside the profile and can be written back into the model provider's settings. A hard re-fetch drops every cache and asks the adapter and all relays again. A switch, on by default, lets relay routes whose models declare text-only input accept images in memory, without editing configuration files. The hidden list is stored in the profile patch and mirrored to $DSH_HOME.

Browses the awesome-claude-video-skills catalog (373 entries) inside DSH settings and installs a chosen skill into ~/.claude/skills and/or ~/.dsh/skills: it downloads the GitHub archive of that repository and copies the skill directory, and executes no code from the repository. Installs run as background jobs with live progress (bytes downloaded, files copied) and can be cancelled; skills installed by the plugin can be uninstalled, while directories without its marker are left untouched. Rows show an approximate repository size reported by GitHub. The same actions are exposed to the agent as the video_skill_search, video_skill_install and video_skill_uninstall tools.

Windows-only. Counts the dsh-auth-* login cookies the DSH desktop shell has accumulated, shows how much of the 16 KiB request-header budget they eat and how many launches are left before the shell stops opening with "desktop welcome: Web authentication failed". The web UI gets a draggable floating card that re-checks every 10 minutes, keeps one snapshot per local date and can refresh on demand; a standalone Windows checker ships in desktop/.

Chrome/Edge companion extension: select text on a page and click the badge to get a Markdown answer from dsh in the side panel or a floating card, with native multi-turn follow-ups; host-side tools let the agent read the current page, capture HTTP traffic and drive the browser. Fork of stuarthu/dsh-chrome (MIT): upstream supplied the bridge, browser tools and page injector, and this fork adds select-to-interpret, native multi-turn follow-up, in-panel settings and appearance options. It registers the same browser_* tool names as the upstream, so the two cannot be installed together.

Windows terminal dock inside the DSH web GUI. It is the occupant of the shipped shell.bottom slot: showing it splits the screen (the columns shrink instead of being covered), hiding it returns the space and keeps the PTY session alive. Each session is a local ConPTY child spawned through node-pty and rendered by xterm.js over a loopback-fenced WebSocket (backpressure, debounced resize). Other plugins can add terminal or DOM views through a host registerView API and a window CustomEvent channel.

Turns every file artifact the agent names in chat into a clickable entry — and refuses to paint one that does not resolve. Hover resolves asynchronously, and only a file that really exists becomes a hand pointer with a dashed blue outline (30 s TTL cache, so repeated hovers cost nothing); confirmed non-artifacts stay plain text and the right-click falls through to the host menu untouched. Left click reveals the file in Explorer already selected (Shell.Application Explore plus SelectItem with SVSI_ENSUREVISIBLE, so the pane scrolls to it; explorer.exe /select is deliberately not used because it silently drops the selection when an instance is already running). Right click offers seven actions: preview in DSH's built-in sidebar, open with the default app, reveal in Explorer, save as, copy the file itself to the clipboard, copy the absolute path, or insert the path into the composer. Ctrl or Shift with left click opens with the default app, Alt with left click copies the path. Names resolve through the absolute path, the session workspace and every profile workspace, then a cached basename index built with a depth budget, shrinking from the left when a mention swallows leading words. The host half also keeps six system-prompt rules resident, so absolute paths stay in tool arguments while the body shows only file names, and every route is loopback-only.

Samples a video the way a person does instead of downloading it: metadata and chapters first, then timestamped frames as images, subtitle-first transcripts (local ASR only when the platform carries no subtitles), AudioSet 527-class sound tags and top comments — 21 tools sharing one on-disk cache behind a cross-process lock. Needs Python 3.10+, ffmpeg and the vidlens package (pip install vidlens-mcp); a missing install comes back with the two ways to fix it instead of a bare ImportError.

Customizable startup animation for DeepSeek Harness with eight bundled clips, random rotation, tail fade and time-of-day greetings. Based on lxj5820/dsh-boot-animation, so do not install it with the upstream plugin; bundled clips and the welcome voice carry their own media terms.

A biomedical Research Graph grounded in literature and experiment results. Fork hypotheses, connect evidence, advance research.

Export a whole working DSH home — profile, installed plugins with their node_modules, skills, hooks and task boards — into one .dshpkg tar and import it on another machine without network or pnpm; also streams over HTTP or a one-shot LAN link.

A working Remotion prototype that turns a DSH plugin repository into a 16:9 promo video and a 3:4 promo image locally; its DSH bundle is scaffolded but has not yet been loaded into a real DSH profile. Requires Node.js 22+ and Chrome or Chromium for rendering.

Four palettes for the DeepSeek Harness web UI — solid, glass, volume and neon — each with light and dark halves. Neon adds a scene light field with a 46px circuit grid, a laser scan that sweeps the conversation column only while a turn is running, HUD-style workspace labels in the sidebar, embedded MiSans Latin chrome type, and a 125% sidebar type scale that stays fixed while the conversation area zooms.

Preset doctor for agent presets: scans home/profile `cordis.patch.yml` declarations and legacy `.agent-presets/` dirs across host lines 0.1.0→0.2.0, shows every detected preset as an official-style card (source/era badges, broken red border, per-finding details, current DSH version + era catalog), and syncs a preset to the current syntax per-card behind an explicit confirm dialog (.bak backup + atomic write; report-level findings are never written — startup scans are report-only). npm: `dsh-preset-doctor`.

A daily journal the agent keeps: the journal_record tool appends dated todos and memories, with optional detail and tags, to one JSON file per day under the DSH home; the right sidebar draws those files as a month calendar marked per day by open todos, finished todos or memories, with checkable todos and the selected day's entries below; and the duty sentence it adds to the system prompt is editable from the calendar itself.

Enhanced right-sidebar files panel: rename, create, upload, download (a directory is zipped on the fly), copy the full path and delete from the tree; an editable document renderer for 128 text extensions with Ctrl/Cmd+S save and conflict detection; plus an independent bottom terminal panel with tabs and a quick-command library persisted under the DSH home.

One hub over every coding IDE you run — dsh, Claude Code, Codex, ZCode, Qoder, CatPaw, Trae, OpenCode. Zero-API: it reads each tool's own on-disk state and gives a session inventory, per-IDE usage with cache-hit rates, one-line resume commands, and a single .hub/ rule body wired into all eight via marker-delimited pointer files. The domestic-IDE adapters (Trae/Qoder/CatPaw) were verified against the installed binaries — a gap no overseas tool covers.

Project-level memory built around a ledger whose structure the AI designs per project; the plugin only handles detection, injection, write-back, archiving and git. Memories are split by meaning: the active ledger holds current state, the turn journal is append-only, and decisions, the goal tree and lessons are one-card-per-file (with a multi-dimension index over the card folders); the fundamental principles file can be changed only by the user. There is a single compaction mode: before compacting, the AI sorts the work into three buckets - what must stay in context and is re-injected verbatim, what is written to the project's _stash/ for later lookup, and what is dropped. When a conversation is opened in a container workspace holding several projects, it can be locked to one sub-project (the lock lives in the plugin's own home and survives restarts; it leaves no marker in your project). Also an activity log with five levels, where L4 stores the user's own words verbatim (never injected, queryable on demand). Before each compaction a verbatim capsule (user quotes, raw errors, changed files) is written to disk, and both the capsule and its source material survive a restart; a handoff document lets a new conversation resume the previous one. 21 tools, 12 subcommands, 39 settings (one of them switches whether the settings panel or each project's manifest wins). Runs locally, no runtime dependencies.

Browser provider for DeepSeek Harness: hand it a web task — open a page, click, type, fill a form, read what is on it — and it drives a real browser step by step, seeing an indexed table of what can be done on the current page instead of raw HTML or screenshots. Each step is one bundled-Jev decision rather than a full model turn (1.1 s median per step versus 2.8–3.6 s for chat-model turns in the repo benchmark), and the main conversation receives only the conclusion, so its context does not grow with the page. Targets come from the page it just read and a changed page is re-read rather than clicked blind, and it runs in the browser that Session owns, leaving your everyday Chrome untouched unless you switch to attach mode.

Run one instruction on every online Windows and macOS machine, across networks and regions: a dependency-free relay talks to each machine over outbound connections only (Tailscale, a public VPS behind TLS, or a tunnel), every machine runs the command in its own checkout, and results come back with a commit, a working-tree fingerprint and a command hash so an environment mismatch is reported as unverifiable instead of being mistaken for a different result. Sending work needs its own operator token, separate from the per-machine device token.

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Windows 2000 desktop skin for the DSH Web GUI: metric-accurate grey chrome, two-tone gradient title bars, 1px bevels, square corners, 16px scrollbars, and the pixel font it renders with served by its own host route.

Connects the Xiaozhi voice assistant to DSH Web over MCP: DSH is the tool provider, weaving 35 DSH Web endpoints into 16 voice-friendly tools for workspaces, sessions, chat, models, settings and files — outbound WebSocket to the Xiaozhi MCP access point by default (no public IP or port forwarding needed), several devices bound at once, plus a DSH settings page with live status.

Local TXT reader in a right-sidebar tab plus a spoiler-safe AI reading companion: the model only sees what you have already read — the current chapter, the tail of the previous chapter, and a per-book background file it grows as you go. Excerpts, thoughts and the companion replies become structured Markdown notes exportable to Obsidian; raw text unlocks only for a book you mark as finished.

Fireworks celebration engine: floats fireworks above the chat window while the agent codes — welcome show, per-turn salutes, tool sparks, milestone celebrations, a finish finale and a dud on failure; each event type has its own fireworks card group with random variants, and token usage decides firework size, height and splendour.