Plugins

White-box memory in two parts: four user-authored long-term tiers (must-follow rules, behavior settings, user profile, optional rules) injected as one system-prompt section, plus a separate temporary working set (cross-session handoffs, stage goals, waiting items) with its own 1200-character budget that stops being injected once an entry is done. The long-term tiers are plain Markdown files the user can read and edit; the agent can only propose them, and nothing is written until the user accepts in the Chinese panel. Temporary entries are written only when the user explicitly asks, and live in <DSH_HOME>/temp-memory.json (created on first write), not in the memory directory. No auto-capture, no background writes, no network.

Capture a Windows window to a WSL file, whole or cropped to a region or to a named UI element.

Windows desktop automation for dsh: 14 tools that enumerate apps and windows, capture window screenshots that still work when the window is covered by other windows, read the accessibility tree, and perform real input — click, type text (CJK included), press key combinations, scroll and drag. Loads the official computer-use runtime (@oai/sky) already installed on the machine, discovering it by enumerating vendor directories, so vendor upgrades that change hash directories do not break it.

Read-only tmux list + capture-pane.

Closes ai-memory's consolidation loop for DSH: when a DSH session ends it calls ai-memory finalize-session, so the observations DSH captured become wiki pages the other harnesses ai-memory serves can read. Skips subagents, queues concurrent session ends, and sweeps sessions abandoned by a forced restart.

Windows desktop control exposed as native DSH tools - whole-screen and single-window capture (the window one goes through PrintWindow, so a covered window still captures), click, drag, typing, keyboard shortcuts, scrolling, window management, pixel and window polling, and UIA queries that can invoke a control or read its value instead of clicking coordinates. 11 tools over a PowerShell 7 child process; no MCP server, no resident process, no API key.

Capture selected DSH, local MCP, or native WebMCP calls as reviewed, parameterized routines, expose typed tools, and replay with fresh approval.

Point-and-shoot screenshot capture: a system floating window turns a new screenshot (or copied image) into an Obsidian note with comments and key-point marking, instant OCR through the host DSH multimodal model (no extra API key needed, Tongyi Qianwen as fallback), a duplicate-screen guard, per-day merging, and an optional evening AI organization pass.

Erfasst KI-Web-Unterhaltungen in lokalem JSON + SQLite und portiert ausgewählte Nachrichten als lebende, fortsetzbare Sitzungen in Agenten-Harnesses.

LLM-Debug-Konsole für DeepSeek Harness: erfasst den vollständigen Inhalt jedes Modellaufrufs am llm/stream-Waterfall (Optionen, Stream-Chunks, Usage, Wire-Protokoll) und zeigt ihn in einem DevTools-artigen angedockten Panel an, mit Shared-Prefix-Kontext-Diffing, Wire-JSON-Rekonstruktion, JSON-Export und einer zur Laufzeit abstimmbaren Capture-Policy.

Bildtools für das Chat-Eingabefeld (Eigenentwicklung): Bild-Upload (≤10 MB zum Schutz vor Token-Verbrauch) + benutzerdefinierter Bereichs-Screenshot (Electron desktopCapturer), injiziert in DSHs Entwurfs-Bildspur. Null externe Abhängigkeiten.

Bildschirmaufnahme und externe Bilderkennung: take_screenshot-, list_windows-, analyze_image- und view_image-Tools mit konfigurierbarem GPT-Vision-Kanal (gpt-5.5 / gpt-5.6-sol / gpt-5.6-terra), API-Schlüssel über den Credentials-Service und eine Einstellungs-Karte; view_image zeigt den Screenshot in der Weboberfläche, während der Modellkontext nur Text enthält.

DeepSeek-Harness- (dsh-) Plugin, das die lokale Desktop-Plattform „Screen Automation Helper“ (Windows/macOS) in das Agent-Tool-System einbindet. Stellt Status, Fähigkeiten, Workflow-Liste/Ausführen/Stopp, Run-Management, Screen-Capture und lokale Erkennungsprimitive bereit.

Browser-lokales Audio-/Video-Toolkit für DSH — Frames extrahieren, Thumbnails erfassen, Bilder komprimieren und Clips mit FFmpeg.wasm in GIF konvertieren.

Exakte Profilsteuerung deines echten angemeldeten Chrome-Browsers: ein MCP-Server plus MV3-Erweiterung und authentifizierte localhost-Bridge für Tabs, Locators, Datei-Injektion, Medienexport und dauerhafte Scroll-Aufzeichnung, ohne Debug-Profil oder Remote-Debugging-Port.

Erfasst jede Upstream-Modell-API-Payload als JSON (Debugging und Observability).

The 7-7-7 execution loop for DeepSeek Harness — plan, run, capture, close, compound, with a human gate.

DeepSeek Harness plugin: saved shortcuts (name + target agent + text) with a workspace/session/agent tree picker, a sidebar menu that delivers a shortcut's text to its target without switching sessions, and per-message capture from user bubbles

Captures and compares single-token behavioral fingerprints of configured DSH model routes using the One Token Is Enough protocol.

Forward WeChat chat records into DSH sessions: a Windows share target captures the merged-forward ZIP, an in-GUI overlay picks the destination workspace and session, and the ZIP arrives as a file-attachment user message the agent unpacks and reads. Media entry extensions are normalized by magic bytes (WeChat ships PNG/HEIC bytes named .jpg), and failed deliveries preserve the batch for retry. Requires Windows 10/11 with Developer Mode on and the repo installer to register the share target.

Reads a video or audio file into metadata, sampled stills, subtitles and a multilingual speech transcript with speaker labels, captures the live desktop as frames or a recording, and installs its ffmpeg/whisper.cpp/sherpa-onnx toolchain on first use with per-file sha256 checks; all processing stays local. Automatic toolchain install and desktop capture currently support Windows x64 only, so elsewhere ffmpeg and model paths must be set manually.

Long-term memory on top of mem0 and a local Chroma store: user profile and recalled facts injected through the system prompt, capture at session end, a nightly pass that dedupes, merges paraphrases and resolves contradictions, a persistent topic graph written as Markdown cards, periodic export to a git repository, and a full-page memory UI with search, bulk merge, snapshots and undo. Needs a manual Python venv setup plus LLM and embedding API keys before use.

ReMe-shaped long-term memory for DSH: Markdown workspace, BM25 recall, turn capture, scheduled consolidation

DSH plugin: 29 deterministic, offline tools for JSON validation with exact line/column, JSONPath queries, YAML/CSV conversion, text diff, regex capture, encodings, hashes, Unicode, CIDR, JWT structure and timestamps. Every call returns a { result, meta }