Plugins

Three ledgers for a model that loses context between restarts. Self-note: what I have become — capped at 40 entries, and every eviction first leaves a one-line crease recording which entry was dropped and why. Judgment ledger: record a claim together with how to verify it, come back when it is due, and mark it right or wrong; wrong ones stay in a mistakes book so you stop assuming you were always correct. Handoff: where this run stopped and what the next one should read first — a baton, not a memory. Three tools each taking an action parameter instead of a dozen separate ones (the prompt is paid every turn). Data lives in ~/.dsh/*.jsonl and is shared with the same-named CLI scripts. Zero dependencies.

Layered global and workspace memory for DeepSeek Harness, with a web panel to browse entries and tune distillation and consolidation, an index kept in context with records loaded on demand, and a per-session choice of layer.

Obsidian-compatible Markdown notes in the DSH sidebar with search, tags, backlinks, graph, audio notes with transcription, a paint canvas, OCR (needs tesseract), client-side encryption and notes_* agent tools; the release tarball and the npm package carry a prebuilt Linux x64 daemon, other platforms build it from source with Go.

Stores the agent's long-term memory as plain Markdown in an Obsidian vault — every memory is a .md file with YAML frontmatter that Obsidian indexes natively, so you can read, edit, link and back up it with tools you already use. Nothing is locked in a database. Ships a sidebar panel (tag filter, sort by recency or importance, edit in place), 7 agent tools, three-tier token-budgeted recall, BM25 ranking (no embeddings, no API key, works offline, CJK bigram tokenization), importance decay with archiving (moved to .archive/, never deleted), and optional GitHub Contents API sync. A note containing a secret is refused rather than redacted, because a redacted memory reads as complete while the important part is gone. Zero runtime dependencies; everything comes from the DSH host.

Moves a conversation into another workspace: long-press its sidebar row, drop it on the target workspace, and the session log with its full history is relocated and re-pointed. A plain drag still does the sidebar's own reorder inside one workspace.

Adds a delete row to the menu of an archived conversation only, and after a confirmation removes the session log directory, its projection cache, the archive and pin marks and the workspace booking together.

Write each session's summary as a Markdown file in its workspace, with a page to browse, regenerate and delete them.

Archives sessions that have gone unused for longer than a set number of days (5 by default); any single session can be marked as not archived.

Read-only monitor for local DSH sessions: live task board, per-session tails, blocking reply wait, Markdown export, and optional IM push via dsh-im. Requires Python 3 with the zstandard package; IM push additionally needs the dsh-im plugin.

Two triggers (a heartbeat and a log marker) that wake a session and let the agent decide whether to say anything; silence is a reply. Off by default: set sessionId (the target session) and enable it in the profile config, and if replies are forwarded to a chat app the send layer must drop the SILENT marker.

Adds an "Add model" entry to the model menu for third-party providers, plus a management dialog that switches the model of the current conversation, edits or removes entries, and highlights the one in use.

Wallpaper skin for DeepSeek Harness: static images, video and generative gradients with five fit modes, blur/dim/contrast/saturation sliders, rotation and six transition styles. A spread mode carries the same artwork into the sidebar, panels, menus and window chrome instead of only the conversation canvas. It also samples the artwork on a 12x8 grid to derive WCAG-checked text colours and surface opacity, and annotates replies with colour only, never boxes.

Floating Token Burn Dock for DSH that aggregates provider usage across every session: the collapsed capsule shows the live tokens/sec rate with an inline 60-second sparkline and today's total, while the expanded panel adds a large live-rate hero, per-model and per-hour breakdowns on a real left axis, and a 30-day commit-style heatmap. The sequence-frame flame burns only while tokens are actually flowing and goes out at rate 0; day and hour buckets follow the browser's UTC offset instead of the host process timezone, and the 31-day record store is written atomically after history load so a restart no longer wipes the numbers.

Hides the sidebar's global panel navigation (Plugins / Market / Schedules / More) and gives the vertical space back to the session list; three modes, switchable in Settings → Sidebar.

WYSIWYG Markdown notes editor in the DSH right sidebar, with tabbed documents, table editing, chat integration, assistant read/write tools, and local file export.

Windows resource monitor for the DeepSeek Harness (dsh) sidebar: samples CPU, memory and clock speed once a minute, keeps a 30-day history and draws separate 24h / 7d charts for CPU and memory (with 85% / 90% alert lines) plus a frequency chart that marks load-time throttling. Reports sustained CPU >= 85% (10 min), memory >= 90% (10 min) and frequency <= 70% of maximum clock under load (5 min).

Replaces the DSH sidebar list with a workspace rail: pinned chats and folders, projects that are folders with their own AGENTS.md and files, a virtualized Recents list ordered by the last finished turn, a project_search tool, unread markers, a collapsed icon column with an unread count and a live browser tab title.

A local overview of installed DSH plugins. It does not install packages — pair it with a plugin market. Fold third-party settings, organize notes/groups with AI, check health and toggle plugins, so nothing gets lost in clutter.

Select any passage in a DSH conversation to annotate it in place; the quoted text, the turn it came from and your comment are folded into the message on send, so the model can tell exactly what each remark refers to.

Prompt manager for DSH: imports prompts from JSON or Markdown sources and DSH's own system sections, then controls what is injected into the system prompt — per prompt, or per agent preset — with title editing, drag ordering, LLM translation and the option to inject either the original text or its translation.

Installiert, aktualisiert und entfernt DSH-Plugins über einen Tab auf der Plugins-Seite. Die Installation ruft den profileigenen In-Process-Dienst pluginManager auf, sodass Plugins bei laufender Desktop-App statt nur über CLI hinzugefügt werden können. Updates laufen über die öffentliche dsh-market-Update-API v1 (für diesen Abschnitt erforderlich) und zeigen gemeldete Phase, Prozent und Download-Bytes als Fortschrittsbalken. Rollback nur, wenn der Market einen restorepoint meldet. Wird das Entfernen eines verwendeten Bundles abgelehnt, deaktiviert es das Bundle, entfernt es aus dem Profilmanifest und reiht Restdateien zum Bereinigen nach dem nächsten Start ein.

Git-Chip neben dem Composer öffnet eine zentrale Workbench (Änderungen, Verlauf, Dateien, Tags, stash) und einen Git-Bereich in den Einstellungen. Multi-Account-OAuth-Device-Flow und PAT, Rechte je Repository (full/read/none). Schreibzugriffe per globalem Schalter, Lesezugriffe nur auf erlaubte Verzeichnisse. Push wird abgelehnt, wenn kein Konto auf das Ziel-Remote schreiben darf. Diffs inline mit Zeilennummern, 4 Layouts, Hervorhebung einzelner Wörter, Syntaxhervorhebung und Suche mit Ctrl/⌘+F; Markdown und Bilder werden inline gerendert. Commit-Nachrichten sind durchsuchbar und aus dem staged Diff per Host-LLM generierbar. 8 Agent-Tools, 51 lokale HTTP-Endpunkte, 8 Sprachen; Tokens at rest mit AES-256-GCM verschlüsselt.

Arbeitsprüfungs-Loop für einen Obsidian-artigen Vault: schreibt den Dream des Tages und einen nummerierten T/G-Plan, führt nur als Routine markierte Punkte aus (standardmäßig schreibgeschützt; lokale Commits nur mit --live), fasst sieben Tage zu einer ISO-Wochenroutine zusammen und zeigt alle Tages- und Wochenangaben in einem schreibgeschützten Seitenleisten-Panel.

Skill-Bundle für gestufte Multi-Agenten-Wissenschaftskampagnen in Mathematik, Physik, Astronomie, Technik und biomedizinischer Evidenz: gemeinsame Tafel, unabhängiger Prüfer und Red Team, Wolfsrudel- und Flankierungstaktiken, Token- und Zeitbudgets, Tests mit bekannter Antwort, ein Pendel-Pilot mit 4 Agenten und ein Pilot vierter Ordnung mit 6 Agenten, der einen Fehler im Benchmark-Lösungsschlüssel fand und korrigierte. Behauptet keine Lösungen offener Probleme.