Plugins

Draws draw.io diagrams in DeepSeek Harness through the next-ai-drawio MCP server: the link in the reply opens a live preview in the right sidebar, you can edit the diagram by hand, and each AI change is a version you can restore. Node.js 18+; npx downloads the MCP server on first use.

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

Connect ChatGPT Codex, xAI Grok, Zhipu GLM, AWS Kiro, Google Antigravity, and Cursor subscriptions to DeepSeek Harness through OAuth and a local proxy.

Draws every branch of a conversation as a clickable tree beside the chat, with favorites, custom icons and colors, branch merge and split, rewind-aware layout, and Claude Code branches that keep their memory.

Kiro model provider with Builder ID, Identity Center, Google, GitHub and credential-import sign-in, automatic token and profile refresh, account usage, live model discovery, selectable reasoning efforts, streaming tool calls, provider stop-reason and context-overflow handling, and token accounting that uses Kiro's exact counters when it sends them and otherwise scales the context-usage percentage it does send by the model's advertised window.

AI-driven drawio: four agent tools (validate, render to SVG/PNG, edit, template) plus a sidebar live board — zero-dependency mxfile-to-SVG preview, embedded diagrams.net editor with save bridge, and auto-open whenever the agent draws.

A governed swarm of six specialist DSH agents — orchestrator, planner, knowledge-base bridge, developer and two reviewers — turns a requirement into a strict phase pipeline where every delivery must prove itself with structured evidence before the next phase may start; reviewers are read-only, code merges only after a review pass, and an append-only event log gives full replay and audit on a live kanban board. Its design draws inspiration from the Hermes Agent kanban.

Controls the Chrome you are already logged into: the model clicks, types, fills in forms, reads pages, takes screenshots and downloads files in your real tabs, including inside same-origin iframes. Runs on macOS, Windows and Linux; needs Chrome 116+ and Node 18+. Works over native messaging and chrome.debugger instead of a listening port. Ships 12 browser_* tools and a cb CLI, dispatches real CDP input events, draws an on-page cursor that also appears in screenshots, and adds a toolbar panel with live status, the controlled tabs and a pause switch. browser_download saves a link, an element's target or a URL with the site's login cookies (following redirects, keeping the server's file name) to the Downloads folder or the session's working directory; cross-origin iframes are named in the snapshot but not entered. The native host and the MV3 extension travel inside this tarball: on first load the plugin copies them into place and writes the native-messaging registration itself, so there is no clone, no install.sh and no python3 - the one step left is adding the extension to Chrome: install DSH Bridge from the Chrome Web Store (https://chromewebstore.google.com/detail/bippcbbbipppmhjkjomgdnjbooecbimo, no Developer mode), or load the bundled unpacked copy at chrome://extensions (the plugin opens that page and puts the folder on the clipboard for you). Until then the tools fail loudly with those steps. On Windows the registration goes into the registry (for Chrome and Edge) and the host talks over a named pipe. A daily CI run on GitHub's macOS, Windows and Linux machines installs the plugin, loads the extension into a real Chrome and reads a page through the browser_* tools.

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.

DeepSeek Harness (DSH) plugin — connects DSH to JLCEDA Pro (EasyEDA Pro) via a local MCP bridge and draws schematics through the JLCEDA extension API.

Draws workspaces and conversations as a 3D star map in the stock panel slot: eight layouts (spiral, rings, armillary sphere, solar system, double helix, irregular web, cubic lattice, radial tree), eight colour themes, a memory-library map of instruction files, skills and skill calls, star-to-star fly-throughs, and a 中/EN switch. Links are drawn only where a workspace owns a conversation or one conversation descends from another.

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.

Right-sidebar page for DSH that draws the current session's repository as a VS Code-style commit graph - colored branch/merge lanes, ref chips and per-commit details - with a working-tree Changes area above it (staged/unstaged sections with inline diffs) for every working tree of the repository; read-only, works with or without dsh-better-sidebar, and follows the session's worktree label when dsh-session-worktree is installed.

Replaces the reasoning-effort dropdown with a draggable snapping slider, and draws 13 canvas effects across five style families (thrust, fluid, fantasy, tech, texture) with three tiers that unlock as the effort level rises. Custom mode combines 10 particle forms with 8 flow trajectories; 9 accent presets and a hex picker recolor every effect, and optional key sounds cover two voice clips, a synthesized duck squeak, a mechanical click and a local audio file.

Sidebar session-title icons: an auxiliary model call on the same route as title generation draws a 24x24 monochrome SVG metaphor shown before each session row title, with disk caching.

Model-facing `generate_image` tool for text-only models: the model asks for a picture in natural language, Gemini draws it via the Antigravity CLI, the image is saved to a configurable output directory, and the tool returns the file paths for the model to use in its work.

Aseprite-style pixel art studio: the AI draws sprites stroke by stroke with selections, layers, animation frames, gradients, symmetry and reference layers, each step rendered live as ANSI terminal frames.

Rewinds a finished turn in place — a button next to your own message withdraws that message and everything after it from the model context, puts its text back in the composer for editing, and optionally restores the files the turn changed through the DSH filesystem service.

Draws an ambient glow along the window edge and a moving light band around the composer, sharing one colour table and each with its own switch.

Durable task-decomposition plans for DeepSeek Harness: the model submits a staged plan with acceptance criteria, every work item then runs on a real department subagent, and the progress panel draws done/running/blocked subtasks as a ring, a stacked bar and per-stage steps. Ships a public security self-assessment structured on ISO/IEC 15408:2026 (Common Criteria) — security target, vulnerability analysis, SBOM and a security policy — with an explicit "no certificate claimed" line, plus a published self-correction record of where v1.8.0 documentation overstated the code (fixed in 1.8.1). Every claim is checkable by the reader instead of taken on trust. One command to install, zero runtime dependencies.

A music dock for the DSH web GUI. A draggable capsule in the bottom-right corner opens into a player card with a queue, previous and next, a draggable progress bar, a volume knob driven by drag or mouse wheel, three loop modes and per-track cover art for resolved links (local files show a vinyl placeholder); audio files dropped onto the card play immediately. Paste a Bilibili, NetEase Cloud Music or QQ Music track or playlist link to resolve it: NetEase and QQ audio is signed by the host into an opaque HMAC token, so the browser never receives a plain CDN address and cannot forge one. A spectrum canvas along the page bottom reads a real AnalyserNode and draws in six styles (dots, bars, blocks, mirror, line, wave) with adjustable width, bar count, sensitivity, glow, height, frame rate and placement; the row is fitted to the container width, falling back to a slight overflow when the gaps would fall below half a pixel. Seven colour themes (whale blue-white, aurora, mint, sunset, rose, neon, mono). The settings section is grouped into interface, theme, playback, links and spectrum, and carries favorites and history tables.

Draws circles, arrows, boxes and text on the DSH image preview, keeps every mark selectable so it can be dragged, scaled or re-edited later, and attaches the flattened PNG to the composer at the original image resolution.

Ranks workspaces holding a session that wants attention to the top of the sidebar session list - waiting on you first, then running, then finished-but-unopened, then just read - and draws those rows with a state bar, tinted surface and coloured title, plus a one-shot settle pulse when a run stops. Every colour is taken from the active theme's own tokens, and the three windows that decide how long a finished session stays promoted are settings.

Execution flow chart: renders the current session's execution as a vertical node flow (turns, user, assistant, tools, approvals, retries, compaction), appended in real time over SSE with auto-follow scrolling — the chart draws wherever the session executes.