Plugins
Browse, filter, and install DeepSeek-Harness plugins.
198 plugins found
dsh-workspace-graph
qrxf/dsh-workspace-graph
Draggable bubble graph of DeepSeek Harness workspaces and sessions in the Web UI: workspaces are large bubbles, sessions are small ones, and lines show real membership. The canvas supports pan, zoom and fit; filters cover workspace, status, type and archive state; search covers workspace names, paths and session titles; native actions open or create sessions, rename workspaces, and archive or restore sessions. Layouts are saved in the browser.
dsh-harness-os (dsh-harness-os)
tinynian/dsh-harness-os
Main UI skin that extends the dsh-startup-screen archive layout to the whole workspace, picking up from the boot animation when it hands off.
dsh-workbench-layout
lsq-dsh-plugins/dsh-workbench-layout
Rearranges DSH Web into a three-column workbench with file editing, Git views, Markdown preview, and workspace terminals.
dsh-mobile-pwa
zylzyqzz/dsh-mobile-pwa
Complete mobile PWA for DSH, built on dsh-mobile-gate: secure remote-access gateway plus install-to-homescreen (manifest + service worker), offline capability, touch gestures (pull-to-refresh, edge-swipe back, pinch-zoom font), agent-done push notifications, and touch-first layout — desktop unaffected.
free-vision-skill
niyongsheng/free-vision-skill
Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.
dsh-plugin-deepeye
favio8/dsh-plugin-deepeye
DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.
dsh-kolmopdf
komoai2026/dsh-kolmopdf
Official KolmoPDF plugin for DeepSeek Harness: six tools for PDF-to-Markdown/OCR with formulas and tables, layout-preserving PDF translation, Markdown export to DOCX/PDF/HTML/LaTeX, cost estimation, and a Settings → KolmoPDF key and live-credits panel. PDFs and Markdown you process are uploaded to the KolmoPDF cloud service (www.kolmopdf.com) with your API key, and conversions use your KolmoPDF credits.
dsh-sidebar-organizer
tlewa/dsh-sidebar-organizer
Adds custom ordering and tucking away to seven strips of buttons and cards in DSH (the left sidebar, sidebar footer, conversation tabs, composer dock, session header icon strip, right sidebar and settings navigation), plus per-area drag switches and JSON layout import/export. Tucked rows land in the built-in More menu of that region and can be dragged back out.
dsh-memory-palace
dafantong01/dsh-memory-palace
Local long-term memory for DSH sessions: archives older turns under context pressure, with a turn-summary index for faster turn lists, statistics, window probing and archive planning (rebuilt automatically when unavailable, with a manual full verification), four tiered hot-memory boards, project documents with enabled/disabled/archived filters and optional owner-controlled family sharing, project hot memory, dual user/assistant turn previews, memory families with editable names and root transfer, root-abdication recovery, orphan-family takeover, summary keyword locator with segment-level candidates and paging, manual injection, 20K segmented reads, and tag-related retrieval. Includes staged recall cues, automatic compatibility with older memory layouts, and post-install version verification. Off in each new session until you turn it on with `/palace on` or the Memory Palace tab. All data stays in the workspace.
dsh-incident-journal
qw2007/dsh-incident-journal
Five skills for a reviewable engineering incident journal: record an event only when a counterfactual can be written, quiz yourself from the existing entries, audit the journal for decay, ingest outside material together with its provenance, and rename a layout directory while rewriting every reference to it.
dsh-mermaid-preview
realguan/dsh-mermaid-preview
Render Mermaid fenced code blocks as native diagram cards with 8 design-system themes and adaptive layout.
dsh-jev-advisor
gordan-code/dsh-jev-advisor
Adds human-facing TypeSafe Jev advice to DSH multiple-choice prompts, on demand by default with optional automatic requests, recommendations, probabilities, confidence, close-call warnings, copyable suggestions, one-click adoption, profile-scoped card layouts, temporary decision preferences, optional request previews with common-credential masking, and local health checks with sanitized diagnostic exports.
dsh-composer-layout
lavapapa/dsh-composer-layout
Web Composer placement for long prompts: keep it at the bottom or dock it in a resizable right column beside a long answer.
dsh-plugins (dsh-mobile-ui)
tzhr-invest/dsh-plugins
Mobile UI for the Web GUI on narrow screens: full-width responsive layout, overlay session drawer, 44px touch targets, safe-area support, and reading enhancements with zero desktop impact.
dsh-visio
samyihu/dsh-visio
Open and edit Visio (.vsdx) drawings in a DSH panel: live SVG preview, shapes, swimlanes and connectors with side-midpoint routing and no-through-shape checks, .vssx stencil import, layout audit, and a visio tool so the agent can read and modify the drawing. Python stdlib engine, no Visio or Office needed; Python 3.9+ on PATH, Pillow for PNG export and snapshots. Requires Python 3 on PATH.
dsh-minimal-ui
superltmajor-pixel/dsh-minimal-ui
Refines the DeepSeek Harness interface for reading by adjusting layouts and reducing persistent controls. Built for DSH 0.2.2-rc.1 (Web UI); other versions are untested.
dsh-app (dsh-mobile-tunnel)
qiaohelenjoe/dsh-app
The mobile client for DeepSeek Harness: use the DSH running on your computer from your phone. The Android app signs in with the same account, picks this computer from the device list and opens its DeepSeek Harness UI on mobile. The desktop plugin handles registration and the connection, and nothing on the computer needs an inbound port. The UI adapts on its own: on a phone it becomes a touch-friendly layout, and returns to the desktop layout when a foldable opens or the window gets bigger. A PC-side panel shows login state, device quota, device list and the app download QR code.
dsh-session-timeline
columforge/dsh-session-timeline
Right-sidebar session timeline: fishbone layout of every workspace session with native fork/handoff lineage, manual drag links, branch fan-outs, archived-session display and per-turn detail browsing.
dsh-sidebar-suite
yonan1269/dsh-sidebar-suite
Adds two switchable sidebar layouts (tabs and overlay) plus a no-override official default, an always-expanded session list, disposable temporary sessions and a third-party tab API to DeepSeek Harness, with default-layout and feedback controls in the plugin detail page.
dsh-preset-studio (studio)
hycally/dsh-preset-studio
A panel for editing DeepSeek Harness agent presets. It reads and writes the files inside a preset, switches its prompt injections, documents, skills and tool rows on and off, and installs or uninstalls the preset. Editing is line based, so YAML comments and layout survive. The same package also ships the injector and the doc_update write-back tool that a preset mounts.
dsh-local-trim
leonlee114514/dsh-local-trim
One-step local model onboarding plus a light harness for DSH. On load it probes loopback and private-network inference endpoints (llama.cpp, Ollama, vLLM, LM Studio), reads each model's context window and output budget from the backend, and registers the provider through settings, so a local model becomes selectable without hand-writing config. It then trims only that provider: masks the tool list through tools.restrict, drops named system-prompt sections and memory contexts, swaps the injected instruction block for a short one while preserving its first 80 and last 96 characters, and truncates tool-schema descriptions without touching structure or required fields. Cloud providers are returned as the same assembly object, untouched. The injected block is re-read from disk on every assembly, so editing the file takes effect on the next request with no reload. The panel in the plugin detail page is a live operations view: it shows whether the takeover is active and by which hook, how many characters the last assembly was trimmed from and to, and which providers are online (probed concurrently, with a real one-shot completion reporting latency and reply text per provider). If a local backend is not running, the panel offers a one-click launch: it probes the port first (never starting a duplicate), then starts the matching server (ollama serve, or a custom command you supply) detached and polls until the endpoint answers, clamping the wait to 3-600 seconds, reaping the child it just spawned if it never answers, and naming the paths it searched when it cannot find the binary. A stop button kills backends this plugin started (SIGTERM, then SIGKILL) and refuses to touch a server somebody else launched. When a model has just been downloaded and no backend exists yet, the panel can also scan the machine for .gguf files with hard caps (300 models, 20000 directory entries, Downloads only one level deep), start llama-server on the chosen one (skipping the .mmproj. vision projection and reusing a server that already answers), register the provider under the model id the backend reports, and run one real completion to prove it works. Before spawning anything it does a fit check that counts only the part of the file the GPU cannot hold: hostBytes = fileSize - VRAM, compared against max(total RAM - 2GB, free RAM). A file far larger than RAM is refused outright; a heavy host-side remainder is refused unless you confirm; the same remainder under mmap is only a warning, because the weights land in reclaimable page cache. A load-mode selector (auto / mmap / none / mlock / mmap+mlock) maps to llama.cpp --load-mode, and the default is whatever the engine picks. From 0.4.2 everything above is derived from the platform instead of assumed: home and data directories come from os.homedir() and the OS conventions (LOCALAPPDATA on Windows, ~/Library/Application Support on macOS, XDG_DATA_HOME elsewhere); backend binaries are looked up in the official install locations of each OS and can be pinned with OLLAMA_BIN, LLAMA_SERVER_BIN, VLLM_BIN or LMSTUDIO_BIN; model discovery walks DSH_LOCAL_MODELS_DIR, ~/models, ~/llama.cpp/models, ~/.cache/llama.cpp and the LM Studio data directory, with the WorkBuddy layout demoted to one candidate among them. VRAM is asked from nvidia-smi, then rocm-smi, then sysctl hw.memsize on Apple Silicon (flagged unified, so the same bytes are not charged twice), and any flip to a unified-memory budget is handled explicitly. Before building a command line the plugin runs llama-server --help once and keeps only the flags that build actually has, so older engines get --n-gpu-layers 99 and no KV quantization while newer ones get auto plus q8_0; anything it cannot probe is passed through rather than dropped. LM Studio is started with lms server start --port N rather than being lumped in with the engines that need a model argument, and vLLM gets its own --model example instead of llama.cpp syntax. Windows, macOS and Linux are all exercised in CI, including a windows-latest and a macos-latest job, because a cross-platform claim that has only ever run on one OS is not a claim. Two of those suites exist specifically to catch this machine's blind spots: one replays the whole suite with process.platform rewritten to each OS, and one deletes every advantage this development box has — no nvidia-smi, no rocm-smi, no sysctl, an empty PATH, a home directory with no models — and requires graceful degradation rather than a crash. That last one caught a real class of bug: several assertions hardcoded 'lms.exe', which cannot pass where the executable has no suffix. Measured on the reference machine: a 16.9GB 27.2B MoE with 14.5GB of VRAM holds a 285-691MB working set and sustains 76 tok/s after a 1000-2000 token warm-up, so file size alone is not a fit signal. From 0.4.3 the scanned models are shown as a table rather than a dropdown (one row per gguf, with its size and any fit warning), so you can see what is on disk before choosing. From 0.4.4 the delete button on the provider table removes the provider entry, not the weights file on disk. That distinction matters: what people actually want to clear out is the dead entry - one pointing at a port that never answered, one registered twice for the same port, one whose model file was deleted long ago - not a 15.8GB gguf. Deleting a config is undone by importing again; deleting a gguf is not. The removal goes through settings.mutate with an unset op on \['providers', id], because update merges layers: writing null there leaves a null provider key that the loader reads as a broken config rather than an absent entry, and only mutate/unset is implemented as Reflect.deleteProperty. The result is read back afterwards, because unset on a key that comes from a lower layer (the profile cordis.patch.yml or a home patch) does not delete it - it restores the inherited value, so the call succeeds while the entry stays. When the entry is still there the panel says so and points at the file to edit instead of reporting success, and a DSH whose settings service predates mutate() is told plainly rather than silently ignored. Deleting takes two clicks and clearing the confirmation is as easy as clicking another row; on success the online and baseURL caches are cleared and the tool surface is recomputed, since the provider list changed. The gguf itself is never touched by this plugin - the scanned-model table is display and selection only.VRAM reporting is driver-dependent. From 0.4.5 model discovery also reads Ollama's own storage: its blobs are named sha256-… with no extension, so extension matching could never list them. Weights are now accepted by extension OR by GGUF magic header (only dot-free files of at least 8MB, capped at 600 header reads per scan; obviously-not-weights extensions like .json/.md/.safetensors/.part are never opened). Ollama models are resolved from their manifests: the model layer is picked by mediaType application/vnd.ollama.image.model (never adapter/mmproj layers), the human-readable name is restored from the manifest path (…/qwen3/8b becomes qwen3:8b, …/latest stays bare), tags sharing one blob merge into a single row, and the metadata kv supplies name, quantization and context length. Adopting an Ollama model does not start a duplicate llama-server over the same weights: it confirms ollama serve answers on 11434 (launching it if not) and registers the provider under the tag the endpoint itself reports — the blob's sha256 name would never match anything, since 11434 lists qwen3:14b, not sha256-a8cc…. Two real-machine-only traps fixed on the way: existsSync('<file>/') returns true on Windows, so manifest-vs-directory branching now goes by parseable content instead of trailing-slash semantics; and the quantization label table had been copied from a stale ggml enum generation, labelling ggml_type 15 as Q5_K_S while ollama show reports Q4_K_M. Same-blob dedup is by (dev,ino), keeping whichever entry has a name. Verified on the reference machine: the scan goes from 1 row to 4 — qwen3:14b (8.64G) and qwen3:8b (4.87G) now appear with Q4_K_M badges — in 4ms; npm run verify exits 0 (launcher 57, portable 35, panel-host green including the linux/darwin simulated-platform runs); the new panel-host suite builds a real miniature Ollama store in tmpdir and points OLLAMA_MODELS at it, so results no longer depend on whether the test machine happens to have Ollama installed. From 0.4.6 the panel shows each model its real name instead of its file name, because some download tooling stores every weight under one generic file name, leaving the real name only inside the GGUF header. The scan now reads each file GGUF KV section - not a fixed-size head buffer, because tokenizer.ggml.tokens (hundreds of thousands of strings on a large MoE model) and the chat template push general.file_type past any window; and GGUF string arrays are interleaved (u64 length plus payload per element), so treating them as a length table walks the cursor off the rails and produces astronomically large reads. Reading and skipping are accounted separately: key names and types are always read, string values over 256KB and string arrays are only walked past without copying, non-string arrays over 64 elements are skipped outright, and a cursor past the file size stops the read, because an out-of-range position means the cursor is wrong rather than that a limit should be raised. The displayed name goes Ollama tag, then general.basename plus size_label, then general.name, then the file name, with the full string kept for the hover text since it usually carries internal build numbers; mmproj files are now identified by general.type as well as by name. A short read (truncated file) no longer feeds half a value into the parser. On the reference machine, reading one file header parses 44 keys in about 16ms, and a whole scan takes about 31ms. From 0.4.7 the smoke test no longer fails the first time and passes the second. The old code gave both request attempts one shared AbortController and one shared 30-second timer, so the total budget covered both rounds: a cold load of a large model burned it in round one, the abort left the signal permanently aborted, and the second round (the Ollama-style reasoning_effort: none retry) could not even be sent - which is exactly why the first click returned This operation was aborted and the second succeeded. Now each attempt gets its own controller and timer, a timeout retries once automatically (retryOnTimeout, on by default) because a first-request timeout almost always means the weights are still being read from disk, and non-timeout errors (refused connection, HTTP error) are not retried at all. Timeouts report themselves: the message says the wait exceeded smokeTimeout, whether a retry already happened, and points at the new smokeTimeout setting (seconds, default 60, clamped to 5-600) - port responding is not the same as tokens coming out, so it is a separate knob from launchTimeout. Unrelated: an example naming one specific model was dropped from the panel copy, since not every machine has that model downloaded, and the explanation now describes the mechanism instead. From 0.4.8 adopting a plain .gguf no longer registers an unrelated Ollama model. The port field used to follow the last click rather than the file: selecting an Ollama entry moved it to 11434, selecting a plain .gguf did not move it back, so a 11434 left over from an earlier click stayed. The server accepted it as given, probed the port, found Ollama answering and borrowed it (the skipped-launch log line about the port already answering is this path), and then the model id - derived from the file name - could not be matched against Ollama's /v1/models, where the fallback was to grab the first entry in the list. Embedding models tend to sort first, so the adopt registered a model the user never selected. Now the port follows the file: a plain .gguf landing on another engine's port (ollama 11434, vLLM 8000, LM Studio 1234) is moved to 8090 and the panel says so. Only ports belonging to a known engine are overridden - a hand-typed 9999 aimed at your own llama-server is left alone. The model-id fallback no longer guesses either: it takes the only entry when there is exactly one (a single-model backend may legitimately report a different id than the file name) and otherwise reports an error listing the ids it did see, rather than registering a wrong provider. From 0.4.9 the panel can no longer vanish. It used to be possible for the whole section to disappear from the plugin detail page while the host stayed up, the HTTP bridge kept answering, and no crash log appeared. The cause was a scope error: a helper was declared inside one component and referenced from another, which is valid JavaScript and passes a syntax check, so it only threw at render time - when the user pressed the scan button and React ran the state updater. The host wraps every slot entry in an error boundary whose fallback is an empty anchor, so the throw was contained silently: the panel was not uninstalled or crashed, it was replaced by an empty div. The helpers now live in the module scope both components share. The client half also gained its own test - a minimal React stand-in loads the real panel module, really calls the components, really runs the state updater at render time, and presses the scan button, so this class of error can no longer reach a release.
dsh-token-gauge
liumiaozhi/dsh-token-gauge
Sidebar token gauge for DeepSeek Harness: live output-speed dial, current-session and today token totals, estimated spend from DeepSeek list prices with half price off-peak, and a 70-100% cache-hit dial, with single- and dual-gauge layouts and four skins.
dsh-market-peek
lyuyuxin/dsh-market-peek
Previews plugin-market entries inside DSH instead of opening an external browser: clicking a card shows the README in a panel docked beside the market, or the repository in DSH's built-in right-sidebar browser, and restores the layout when you leave. Works with dshmarket and DSH's built-in experimental market.
dsh-docx-format
romebody/dsh-docx-format
Normalizes every generated .docx to one Chinese official-document layout: XiaoBiaoSong title, FangSong body at a fixed 29pt leading with zero paragraph spacing, character-unit 2-character first-line indent, fully centered table cells with repeating header rows, and a centered footer page number. Long attachment entries are split into real paragraphs at the wrap point measured by Word, producing a 2 / 6 / 5 / 6 character indent ladder. It applies the layout only when the request mentions 公文 (official document) and writes no signature block unless asked.