Plugins
Browse, filter, and install DeepSeek-Harness plugins.
3301 plugins found
dsh-theme-plugin
beizi6/dsh-theme-plugin
Theme studio for the DSH Web GUI: five built-in presets plus fully customizable light/dark palettes (accent, background, foreground, UI and code fonts, translucent sidebar, contrast), hot-swapped instantly and persisted in localStorage.
dsh-sleep-send
awu12277/dsh-sleep-send
Schedule-send button and panel to the right of the composer, with smart time slots, a custom date/time picker, several queued sends at once, and localStorage persistence that restores pending tasks after a page reload.
dsh-plugin-chat-mode
xiaofeng7418/dsh-plugin-chat-mode
Adds a tool-free Chat preset for everyday conversation: no tool schemas are sent, the system prompt is one short tone line or empty, and no OS, git or file-tree snapshot is injected. Measured on a plugin-heavy install, one message costs about 1.9K instead of 36K input tokens (roughly 19x fewer); thinking starts off unless you turn it on; verified on Android DSH Go too.
dsh-carry
winlin926/dsh-carry
Remote control of DeepSeek Harness from a phone browser: scan a QR code, confirm the device on the computer, then chat, answer tool approvals and preview workspace files in the host's own web interface. Connects over the same Wi-Fi (with an optional https domain) or through a self-hosted public relay node.
dsh-rugu (dsh)
qiuyedx/dsh-rugu
Persona memory for DeepSeek Harness: one memory shared by every entry point (DSH desktop, and QQ through the dsh-qq bridge) that records what the agent itself experienced. Raw messages are kept, five recall routes (vector, keyword, people and events, time, who is present) run before each reply, and a per-context check decides whether a remembered thing may be said. Adds memory_recall, memory_note, memory_fix and memory_look tools and a Settings page; embeddings are optional (local Ollama or an OpenAI-compatible endpoint).
dsh-freebie-radar
stallenlu/dsh-freebie-radar
DSH plugin for ZiChuanLan/freebie-radar with a freebie_radar agent tool and a sidebar workbench panel mirroring the original site, with channel feeds, search, detail drawer and dark/light themes. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-comfy-suite
elgwia-dsh/dsh-comfy-suite
Merges three MIT ComfyUI plugins into one bundle: workflow library, local image generation and editing (draw, inpaint, outpaint, character, upscale) through a local ComfyUI, plus a service launcher, gallery, style library and prompt wardrobe. Personal merge project, not the upstream version.
dsh-plugins (dsh-dev-git-graph)
kp-z/dsh-plugins
A Git Graph tab for DSH Web: a faithful port of vscode-git-graph 1.30.0 that registers a native tab in the dsh-better-sidebar right rail (prerequisite), auto-binds to the session workspace, runs the full git operations (checkout/merge/rebase/push/tag/stash) directly on the host, and opens file diffs in the built-in DiffTab.
dsh-plugins (dsh-feishu)
kp-z/dsh-plugins
Feishu/Lark task bridge for DSH: syncs a managed Feishu task list and watched documents into a local snapshot, binds a task to a DSH session so progress, ETA, dependencies and completion write back to Feishu, and schedules work through DSH automation. Adds a Feishu tab in the right sidebar (requires dsh-better-sidebar) and a host-page Tasks panel with run bubbles, insight charts and a dependency canvas.
dsh-edge-companion
airainal/dsh-edge-companion
Connects DeepSeek Harness to a logged-in Microsoft Edge through a local bridge and MV3 side panel, and exposes CDP actions on real tabs.
dsh-token-steward
jiamingshi-jsphys/dsh-token-steward
Local OpenAI-compatible gateway that pools several upstreams behind one base URL and routes each request by task profile: hard filters drop models that lack a capability tag, cannot fit the context, or were switched off, then a scorer ranks the rest and an ordered fallback chain takes over. Handles 429 cooling, 5xx breakers, 401 delisting and context-overflow re-routing inside a single client request, caches replayable requests locally by SHA-256, and keeps a per-route token and cost ledger. Vendors, keys and prices are edited in a settings page or by the agent through its manage tool and skill.
dsh-doubao
ralsei1337/dsh-doubao
Rewrites DSH model output as "Doubao-speak": a barrage of superlatives, a long list of negations, healing diagnoses, verbatim repeats and a service-style closing question. Five strength levels (off / light / standard / heavy / max) instead of a dial, two independent channels (system-prompt style bible and llm/stream post-processor), three transform modes, and every length knob adjustable live in a settings page with a preview.
dsh-quadrant-todo
ziye-jk/dsh-quadrant-todo
Four-quadrant todo manager in the DSH sidebar with month and week calendar views, per-period completion statistics, system notifications and Feishu notifications (the latter needs the DSH Feishu integration), and recurrence rules including Chinese statutory workdays and the Ebbinghaus curve. Derived from Natte/dsh-sidebar-todo 0.2.3 and largely rewritten; do not install both — they register the same /todo/api route and use the same todos.json data file.
DSH_Eplan
shangyunqiang1/dsh_eplan
EPLAN Electric P8 automation for DeepSeek Harness (Windows): a bundled eplan-mcp server drives the running P8 2025 instance through the EPLAN Remote Client interface, a settings page sets the EPLAN install root, and five skills cover connection and safety, C# scripting, documentation lookup, EEC Pro development and setup. Five offline SQLite documentation indexes (P8 2025 API reference, P8 2025 platform help, P8 2026, P8 2027, EEC Pro 2026) answer questions without network access, but they are not shipped in the repository: download the release zip or build them with the included scripts; the P8 2026 and P8 2027 rows ship disabled. Requires EPLAN P8 2025 with Remote Client access enabled and Python 3.12+ with mcp and pythonnet (run scripts\setup.ps1 once). A version panel records releases and applies a newer one from the repository.
dsh-pele (plugin)
hesheng01/dsh-pele
Draw Mermaid diagrams in DSH conversations through the pele_draw tool, rendered inline as theme-aware SVG cards with zoom and pan plus SVG and PNG downloads.
dsh-inline-diff (plugin)
him666233/dsh-inline-diff
Inline diff cards for every edit, write and str_replace_editor call: old/new line numbers, character-level highlighting, 57-language detection with a red/green-safe syntax palette, a side-by-side viewer, Read-row line ranges, and a settings page for display style and highlighting.
dsh-theme-animal-island-ui
shirolin/dsh-theme-animal-island-ui
Animal Island theme with boarding-pass masthead, cream notebook paper, 118 ThemeRuntime tokens, in-app appearance presets, and starry night mode.
dsh-oracle-gate
cresbigb/dsh-oracle-gate
Acceptance gate for DSH: freeze the acceptance criteria into an oracle ledger before work starts, then honor only real execution receipts — files changed after freezing are refused outright, and a failing hard gate overrides any human pass.
dsh-copyright-kit
lucky020/dsh-copyright-kit
Turns a repository and a software name into Chinese software copyright registration material - the 60-page source code excerpt (50 lines per page, auto-paginated), the software manual with screenshots, and the derived application-form fields (line count, language, completion date, function summary). Requires Python 3 with python-docx, and Google Chrome for screenshots.
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-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-ikunchick-pet
stitchmaps/dsh-ikunchick-pet
A bottom-right pixel-art basketball-chick desktop pet for the DSH Web GUI: sprite animations, drag with edge snapping, click sounds, waiting reminders when a session needs you, per-turn cost bubbles, a usage ledger, and a DeepSeek balance badge.
dsh-phone-mirror
liyuhan7/dsh-phone-mirror
Mirrors an Android phone or tablet into the DSH right sidebar over adb with mouse and keyboard control, keeping videos, clips and chats next to the desktop instead of in your hand; Opus audio needs Android 11+, Windows only.
dsh-autocad-bridge (bundle-autocad-ui)
cmm00100/dsh-autocad-bridge
Drives the installed AutoCAD over COM and exposes it to the agent as 18 mcp__autocad__ tools: connect and status, cancel the current command, list registered ProgIDs, list or create documents, save, create and list layers, draw lines, circles, rectangles, polylines, arcs and text, list entities, zoom to extents, and pass any native command through. A sidebar panel owns the Python bridge process — start, stop, restart, dependency bootstrap, live logs and crash recovery — and resolves every path at runtime, so the same bundle serves both the web app and the desktop app. Windows only, Python 3.10-3.12, AutoCAD 2022-2024 documented (2024 is the default; other versions require setting CAD_PROG_ID to the matching ProgID).