Plugins

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.

Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.

Lets the DSH agent operate your Windows apps and web pages: it reads controls through UI Automation, clicks, types, captures the screen and reads text with OCR, and works on web pages in its own browser in the background, without moving your mouse; when it needs your mouse or keyboard, an on-screen indicator appears and Esc stops it.

Local IMAP invoice download, OCR, archive, and Excel reimbursement summaries for DeepSeek Harness.

A live iOS Simulator or USB-connected iPhone inside the conversation: 22 agent tools for booting, building, driving the UI by accessibility identity or OCR text, list-row actions and SwiftUI preview hot reload, plus a streaming sidebar panel you can tap and drag on.

DeepWatch's capabilities, installable into an existing DeepSeek Harness profile

A live Android device inside the conversation — emulator or USB phone, driven entirely through adb: 20 agent tools for streaming, Gradle build and run, UI-tree or OCR interaction, logcat, processes and memory, plus a three-button navigation panel.

Local IMAP invoice download, OCR, archive, and Excel summary bundle for DeepSeek Harness

OpenMAIC: classrooms, slides, interactive widgets, and Socratic teaching.

Knowledge base for DeepSeek Harness: assembles ContextWindow evidence at query time within heading boundaries and token budgets, with follow-up reading around each search anchor; combines BM25/vector search via weighted RRF, MMR and optional local/remote reranking; provides automatic evidence injection, a browser panel for local embedding/rerank/OCR model downloads and health checks, keyword search without model downloads, and in-place rescans of imported directories.

Consumer panel for OpenBiliClaw inside DSH: a right-hand drawer with recommendations, saved lists, Socratic dialogue, profile and settings, plus 22 Agent Bridge tools so the agent can read recommendations, answer probes and save items. Requires a running OpenBiliClaw backend with Agent Bridge v2 (default 127.0.0.1:8420).

Image "reading" for text-only models: downscale + reduce color depth + structure/color fingerprints into text grids fed back to the conversation, letting the model zoom, sample and OCR autonomously like a multimodal model; fully local with zero external model dependency, ships an image-reading methodology skill and optional PaddleOCR.

Provider-independent DSH document parsing powered by MinerU, with native background jobs, immutable results, and safe request coalescing.

Pluggable design canvas inside DSH — standalone Excalidraw board, session image tools (edit, erase, background removal, OCR, vectorize, PSD/text rebuild), project asset library, and a Photoshop/Illustrator ⇄ canvas bridge.

Reads bilibili video as structured text for AI: metadata, comments, danmaku, subtitles, local ASR, frame OCR. Local processing (no cloud upload), decoy-subtitle detection with frame check, instant re-reads via cache, AI-ready manifest + summary. Frame OCR needs ffmpeg; local ASR/OCR need Python 3.10+ venvs (plus the VC++ runtime on Windows); AI subtitles need a Bilibili login.

DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.

Research Agent skills, literature search with citation tracking, document-to-markdown knowledge base builder, and in-depth reading with browser workbench for DeepSeek Harness.

Vision-first Mac computer use, for when the accessibility tree is unavailable. Ships 11 desktop_* tools - window list, screenshots, OCR text targeting, numbered elements, coordinate clicks, typing, scrolling, drag - plus a Codex-style cursor overlay with spring animation. Clicks are delivered to the target process, so the real pointer never moves and nothing steals focus. In DSH it shows up as Mac Desktop Control with a settings page that checks the engine and the Screen Recording / Accessibility permissions, with a button that opens the matching System Settings pane. Works out of the box: the tarball bundles the dsh-cu engine and the overlay as prebuilt universal binaries (Apple silicon + Intel, macOS 11+, ad-hoc signed), compiled from the repo's Swift sources by the release workflow - no clone, no Xcode, no install.sh. The only setup is granting DeepSeek Harness Screen Recording and Accessibility once. macOS only; on Windows and Linux the plugin loads without registering the desktop tools.

Media and vision workspace for DeepSeek Harness: image, video and speech generation, image Q&A and element locating, long-image OCR, pixel diff, HTML-screenshot verification and video summarization, with DashScope and OpenAI-compatible providers, model pools and a workbench client.

FormatForge: forge 30+ file formats (PDF, DOCX, PPTX, XLSX, EML, EPUB, TOML, archives) into AI-readable text via a drag-and-drop inbox, ff_translate/ff_formats/ff_result tools and a CLI; scanned PDFs fall back to local OCR or an enhance hint for the session model.

Learning Mode agent preset: a coding agent that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style; installable via dsh plugin add (dsh-learning-mode on npm).

Local PDF, Office, image, and OCR document intelligence for DeepSeek Harness.

Five tools for reading a video as raw material rather than as something to watch. video_outline maps a whole file as text and draws nothing at all: 4-60 equal windows, each with its cut count, speech share, intensity bar and tags, then the windows worth opening and the exact start/end for the call that follows -- zero image tokens. video_probe returns metadata and a reading plan without decoding frames. video_storyboard turns a window into one contact sheet plus a text index binding every cell to its timecode, cut count and frame time; cells whose text would be illegible at that scale are marked zoom, and dedupe global folds a picture that comes back after a cut. video_zoom re-renders 1-9 cells from a short window at a larger scale. video_read decodes only keyframes, OCRs each screen, and returns an outline plus \[mm:ss] text -- the path for lectures, slide decks and screen recordings, where the words are the content. It also reads a file with sound and no picture as a transcript (subtitle track, then DSH_ASR_CMD, then a transcript file you pass; long audio is cut at 45 s onto silence), composes six changed frames into one sheet when a file has no readable text at all, and can write the result out as SRT, WebVTT or text. Cuts, dissolves and one-frame flashes are found in a single ffmpeg pass; from ten minutes up a file is analysed on its keyframes only, 2.7x faster on a two-hour lecture; and a cell is never shrunk below a fifth of the source, so a 1440p sheet spends the same tokens on fewer, bigger cells. OCR is the engine Windows ships, tesseract with line boxes, or DSH_OCR_CMD. It takes a B station link (bilibili.com/video/BV..., a bare BV id, an av id or a b23.tv short link) wherever it takes a file: up to 300 seconds is read from the CDN in place with nothing written to disk, longer videos are downloaded once and cached within a 4 GB / 24 video budget, play URLs are cached for ten minutes, and a link that is not a single video says what it is. Needs ffmpeg, uses ffprobe when present, and has no other runtime dependencies. It is a wire-compatible reimplementation of SAOS-3624/dsh-video-storyboard: it registers the same video_probe / video_storyboard / video_zoom tool names, so the two cannot be enabled together.