Plugins

Generative background music while the model streams, plus completion, approval and attention chimes: hear whether the agent is thinking, still working, or waiting for you without watching the screen.

Meeting notes for dsh: one meeting per conversation, transcribed and speaker-separated on the machine itself, with points, assignments, handwritten notes, reviews and monthly scores in the same panel. Exports SRT/Markdown/Word and packs a meeting into a portable zip another dsh can import; confirmed assignments go to DingTalk/WeCom in one click, following your robot settings. Recognition models are swappable (a stronger local model can be imported from a file), and cloud recognition is off by default with no request made before consent. Word export needs Python and python-docx; the first run downloads a recognition model (28 or 77 MB).

Search public-domain libraries (Project Gutenberg, Wikisource, Internet Archive, Standard Ebooks) by title, author, character or half-remembered plot, or import EPUB / PDF / TXT / DOCX / Markdown, and listen in the sidebar with Microsoft Edge neural voices, offline Kokoro or the device voices; keeps your position, takes voice notes anchored to what you just heard, and discusses the book with your DSH model.

Registers two tools for DeepSeek Harness. `doc_ocr` turns scanned PDFs and images into structured text (per-page text, financial tables with a balance-sheet tie-out check, contract-clause hits) through a local RapidOCR engine or a Zhipu GLM-OCR cloud engine, and `doc_preprocess` turns a directory of raw files into an Obsidian-ready knowledge base through a seven-stage pipeline with backend routing and sha256-based incremental skipping. Numbers that fail the tie-out are reported, not invented. The local engine needs Python 3 with rapidocr-onnxruntime, pypdfium2 and Pillow (pip install -r requirements.txt); the GLM engine needs ZHIPU_API_KEY.

Reads a local video or page link with ffmpeg and Paraformer ASR, returning a timestamped transcript plus key-frame images the agent can open; finds candidate videos by keyword and installs its own runtime dependencies on first use. Requires Python 3.8+ on PATH; video_discover also needs a one-time douyin/xiaohongshu login.

Structured image recognition: local sharp measurements plus a cloud vision model return description, OCR with coordinates, object locations and fine-grained attributes in one call; a fingerprint cache makes repeated images return in milliseconds without spending model quota.

All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can cite concrete frames, seconds and speakers — Evidence, not imagination. One failover chain per media, recorded hop-by-hop in meta.attempts (a fallback is never silent): host-registered multimodal models first, then a configured OpenAI-compatible endpoint (comma-separated multi-key rotation), then local ffmpeg frame-sampling / a local ASR CLI, degrading to metadata-only as a last resort. Absorbs modlens battle-tested rules — cooldown keyed only on auth/quota failures and softened to chain-tail (never dropped), redact-before-clip error text, magic-byte sniff that never trusts file extensions. Optional vision-bridge registers a media-lens wrapper into the host model selector so a pure-text model gains image/audio/video sight. Registering / authenticating multimodal models and true inline audio-video upload lean on two companion plugins, declared as optional peers (absence auto-degrades, never errors): dsh-thinking-levels fronts the model config / registration surface, dsh-llm-openai-completions takes over the OpenAI-compatible transport that serializes file blocks into video_url / input_audio. Privacy: media goes to remote providers by default; strictLocalOnly keeps content on-machine. Prerequisites not shipped with the package: ffmpeg/ffprobe on PATH (frame sampling / reencode / duration probe; degrades to metadata when missing) and a user-configured local ASR CLI for the audio fallback. Hosts 0.1.7 / 0.2.0 / 0.2.1 (6 rc, exact engines.dsh enum). npm: dsh-media-lens.

Cloudflare Workers AI media tools for dsh - text-to-image, text-to-speech and speech-to-text. Per-model price badges, a native settings card, reuse of an existing Cloudflare account, and output files named after the model that made them.

Lets the model actually see a video: local ffmpeg samples timestamped stills and faster-whisper transcribes the audio track, so the agent reads real pixels frame by frame instead of trusting a text summary. Fully local, nothing uploaded; reports honestly when the audio has no speech. Windows only; needs Python 3.10+ and ffmpeg installed, and the first video_eyes_setup run downloads about 700 MB (faster-whisper and its model).

Windows x64 only, 0.5.4 preview: two scoped tools (dragon_browser and dragon_desktop) that drive a visible browser through the DOM or CDP and Windows apps through UI Automation, with per-origin and per-executable read/control scopes, batch steps, a physical-Esc emergency stop and a redacted action log. 0.5.4 only widens the DSH compatibility range to 0.2.0-rc.2 through 0.2.1.x, because 0.5.3 pinned it to an exact DSH version and was silently skipped on DSH Desktop 0.2.1. Two long-lived native processes remove the per-action process spawn, so a single key step takes about 0.7 s on the same machine; when another window steals the foreground the step is aborted instead of typing into the wrong place. The browser side ships its own Edge/Chrome launcher and CDP client, so it no longer needs another browser plugin or the Electron runtime. It is not an OS sandbox; logins, admin windows and secure desktops stay with the user.

Adds a visible-browser Agent preset (persona and toolset for navigating, filling forms, clicking and screenshotting through the Playwright MCP toolset) plus a gate that refuses every browser tool call in other presets until the user approves that Session through the bundled browser_access tool. The bundle mounts the Playwright MCP provider itself, and both a settings page in the Plugins view and the browser_source tool switch the browser at runtime between Microsoft Edge (default), the Chromium shipped with Playwright, and a CDP endpoint. Requires keeping the shared browser-use registration row in the profile (one provider per process).

Installs the codex-cua skill so DeepSeek Harness can use Codex computer use: drives Chrome and native macOS apps through the runtime bundled with the ChatGPT/Codex desktop app, ships a persistent session client and a doctor self-check. Requires the ChatGPT/Codex desktop app with its Chrome extension, Python 3.9+, and macOS.

Agnes AI image and video generation tools for DeepSeek Harness, where long video jobs can be resumed in a later call. Requires an Agnes API key (AGNES_API_KEY).

Registers one `principles_audit` tool for DeepSeek Harness: it reviews a principle library for principle_id collisions and legacy ids, missing causal statements, boundaries, counter-examples or evidence, duplicate and near-duplicate principles, status-versus-confidence inconsistencies, long-stale entries and dimension-coverage gaps. Findings are severity-ranked and a hard gate turns them into pass, warn or fail, where every critical finding must be covered by a valid, unexpired exemption. The library is only read.

MCP gateway for dsh that connects each server on first use and disconnects it after an idle window; tool lists are cached on disk, existing mcpServers files can be imported, and child-process environment variables are scrubbed.

Per-workspace closet for temporary scripts and their run logs, kept in a .dsh-fix directory inside each project. Registers a script with its language and purpose, scans a project for leftover scratch scripts, backups and log files, runs registered scripts with a timeout and writes each run to a timestamped log, and sweeps chosen files into a reversible trash with per-batch restore. Scanning only lists and never deletes; cleanup moves files instead of deleting them; files already tracked by git are refused unless forced. Ships 7 agent tools and a settings panel.

VA Studio integration: ten tools that generate short dramas, images, videos, novels and screenplays, and reverse-engineer prompts from images or videos. Requires a running VA Studio backend.

Deliverables registry for DeepSeek Harness: agents register the final artifacts of a task (reports, pages, documents, sheets, images, datasets) into one settings section and manager page that store paths only, never copies, and remove recoverably; a standalone CLI (add, list, stats, check, remove, restore) reads and audits the same registry outside the app.

Pins a Chinese (zh-CN) thinking and answering constraint into the system prompt, and registers a per-step runtime reminder so the agent does not drift back to English after tool output. Zero runtime dependencies, single file; falls back to a second registration path and only logs a warning when the host API changes.

Turns a Minecraft Java save into a Blender cover or animation: scans the .mca region files for flat open ground, exports the terrain to OBJ, and drives Blender headless with MCprep materials, the BPS character rig and three-point lighting. After each render it reviews the frame with OpenCV for facing, ground contact, exposure, lighting and composition, then re-renders with adjusted parameters when a check fails. Requires Blender 4.2 LTS or newer and Python 3.10+ with opencv-python and numpy; the first run assembles the Minecraft assets with the bundled setup command.

Fork of fourzkw/dsh-drawai that keeps the editable .drawio canvas and its two agent tools, and adds a second vectorization engine beside the original tracer: hierarchical color clustering with Bezier spline fitting and per-channel color precision, selectable per drawing task in three fidelity levels (measured about 18, 38 and 46 dB PSNR on the same 1920x1080 frame (the upstream engine scores about 26 dB on that frame)), with worker parallelism raised to half the logical cores instead of a cap of four. The original tracer stays the default and remains the right choice for whole videos, where the new engine produces files hundreds of times larger.

Requires Python 3.12+; Xiaohongshu reading needs the xiaohongshu-mcp backend and a QR sign-in (ffmpeg/OCR optional). Batch-read Xiaohongshu notes and WeChat public-account articles: per-note body, image text via local OCR, video frame text and comment samples, structured JSON/Markdown output, and the original source URL on every result. Read-only: it never publishes, likes, follows or comments.

Local 3D studio orchestration: detects Blender, COLMAP and ComfyUI on every run and picks the route they support, and also ships a Three.js fallback that generates models from primitive specs, edits or scales GLB files, writes an offline viewer page and renders multi-view PNGs without Blender.

Reference search for DeepSeek Harness: refkit_search looks up image, video, audio and text references across 24 open sources and tags each result with its normalized license and a use verdict for the intended use; refkit_rights re-checks one license against another use. Source keys and search tuning live on a settings page. 11 of the 24 sources need API keys; the use verdict is returned only when an intended use is passed. Runs on DSH ^0.1.7-rc.2 || ^0.2.1-rc.2 (tested on 0.1.7-rc.2 and 0.2.1-rc.2).