Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

1709 plugins found

X

dsh-brain-hub

xxwjxx-1210/dsh-brain-hub

A second brain for DeepSeek Harness where Markdown is the database and git is the sync, with zero runtime dependencies. Core memory is injected into every system prompt, one file per note with weighted search; cards produced in the sidebar web chat land in an inbox first and are approved one by one as cloud notes or local-only notes (private/ is permanently gitignored and never pushed); web-chat progress is saved to progress.md with the last 20 drafts archived. A four-step flow lives behind one header icon: open web chat, extract cards, review them, back up to the cloud. The extraction prompt is editable in the panel and applies immediately.

27 days agoMemoryMIT
G

dsh-github-radar

goodboys155/dsh-github-radar

Right-sidebar GitHub panel with four rising-repository lists — created within 2 days, 7 days, 30 days, and 20k+ stars still pushed — where the first three are ranked by star velocity (stars per day) rather than total stars, so repositories that gained traction fast surface above older ones with more stars. Each row shows the repository name, its own description, language, the stars-per-day rate and up to two topics, and links to the repository. A keyword search box queries the GitHub Search API directly, debounced and IME-aware so a Chinese or Japanese composition costs one request instead of one per keystroke. Reads the public GitHub Search API anonymously: no token, no login, no account, nothing else contacted. Lists cache for 30 minutes and search results for 5; outbound requests go direct first and fall back to a listening local proxy port only if direct fails.

29 days agoUI EnhancementsMIT
S

dsh-tokenlens

senyingxidi/dsh-tokenlens

dsh-TokenLens (词元透镜) — provider-aware plan capacity plus local token statistics (today/7d/30d/all-time, by harness/provider/model/workspace) for DSH.

212 days agoUsage & BillingMIT
T

minecraft-native-mcp

tianyingaquila/minecraft-native-mcp

Opens a browser console to prepare Minecraft Java on Windows x64 and run DeepSeek-controlled survival through native-player MCP tools, with spatial observations and an optional livestream overlay from a separate extension. Requires an installed Minecraft Java Edition 1.21.x client and an official DeepSeek API key with at least ¥1 balance.

210 days agoJust for FunMIT
L

dsh-delivery-kit

lucky020/dsh-delivery-kit

Turns a repository and a running system into acceptance material - database design, design specs, a user manual with screenshots, and test / go-live / acceptance reports. Sections follow GB/T 8567-88; anything it cannot verify is left blank instead of invented. Requires Python 3 with python-docx for .docx output, and Google Chrome for automatic screenshots.

217 days agoTools & CapabilitiesMIT
L

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.

217 days agoTools & CapabilitiesMIT
S

dsh-tri-model

starry-sky-blip/dsh-tri-model

Multi-model layered pipeline for DeepSeek Harness: a strong model plans, a fast one drafts, a third reviews, and a failed review is reworked automatically — endpoints, protocols, models and gates all configured from the DSH settings panel.

212 days agoModels & ProvidersMIT
L

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.

2yesterdayModels & ProvidersMIT
P

dsh-aide

prismscopes/dsh-aide

VS Code-style local IDE for DeepSeek Harness: Monaco editor, explorer, search, Git, terminal, and language services. With pnpm, run `pnpm approve-builds --all` so the native build of node-pty is allowed.

213 days agoUI EnhancementsMIT
L

dsh-popup-cards

leo1958923515/dsh-popup-cards

Bottom-right DSH-styled Windows cards for approvals, questions, plan reviews and finished runs: click to jump back to the app that started the session (DSH by default), close with the × button, or let it close when you return.

216 days agoIntegrations & RemoteMIT
H

claude-on-dsh

huajikano/claude-on-dsh

Runs a project's Claude Code opening questions and plan, hands the task to DSH, and offers post-turn Claude review choices. Windows only, and requires a locally installed Claude Code CLI (set claudeCliPath if it is not auto-detected). New sessions handed to DSH are switched to danger-full-access. The first Claude run in a project folder sets hasTrustDialogAccepted for it in ~/.claude.json, and optional automatic Claude review is capped by a daily budget ($5 by default).

2yesterdayWorkflow & Automation
W

dsh-subagent-switch

wld12314/dsh-subagent-switch

Picks each subagent model from the local catalog by task category, unless the caller already named one. Free and quota tiers are ranked together by per-model capability tags; a pricier model is used only when no cheap model is tagged as good at that kind of work. Only providers whose remaining balance is readable, or that are account-backed, enter the candidate pool; the rest stay listed but are not routed. A panel adds per-model manual priority above the automatic order plus allow/revoke controls.

210 days agoModels & ProvidersMIT
X

dsh-kon-fee-widget

xiao2236/dsh-kon-fee-widget

K-ON! themed tea-table widget: click it to see the DeepSeek balance, today's spend and peak-hour state; each finished turn pops a cost bubble; double-click shows zh/ja character lines.

26 days agoUsage & BillingMIT
Y

dsh-columbina-pet

yuanawaqwq/dsh-columbina-pet

Columbina mascot for DeepSeek Harness: a 2D live pet on the desktop and inside the web panel, with four sprite sets, 76 official voice lines in Chinese, Japanese and English, weather reports, sticker moments, idle whispers, and a right-click menu for the sprite switch interval, sprite set, language and scale. Also includes quiet hours, volume with one-click mute, a searchable idle-action picker, and a power-save mode. It is a 2D-only fork of PC2005-cloud/dsh-pet (MIT) with upstream's 3D skin switching removed; it uses its own plugin id and can be installed alongside dsh-pet.

26 days agoJust for FunMIT
S

dsh-whale-commands

spinoi-code/dsh-whale-commands

Slash commands for the DeepSeek Harness Weixin channel: persona toggle & multi-persona library, session history (soft load or real session switch), model selection, token usage and balance, scheduled daily greetings. Host-side execution, zero model tokens

218 days agoIntegrations & RemoteAGPL-3.0
K

academic-agent (academic-dsh-plugin)

kw78/academic-agent

Local-first academic assistant: event-sourced courses, tasks, plans, reminders, course materials and 23 DSH tools.

218 days agoWorkflow & AutomationApache-2.0
K

academic-agent (academic-dsh-ui)

kw78/academic-agent

DSH sidebar and panel for courses, tasks, plans, connections, course materials, automation and settings.

218 days agoUI EnhancementsApache-2.0
R

dsh-pause-resume

regrevia/dsh-pause-resume

One header button stops running turns, goals and background jobs and writes the plan to disk; after a restart the same button picks the work up again.

23 days agoSessions & MessagesMIT
C

dsh-session-save

chinacaa/dsh-session-save

Saves a whole DSH session as one .dsproj project file and opens it back. The session header gains an open button, a save button, a save-as button and an autosave switch, and the blank-session page gains its own open button. The first save asks where to put the file and later saves overwrite it; opening a .dsproj re-imports the session, switches to it, and can write the bundled workspace memory back on request.

216 hours agoSessions & MessagesMIT
U

dsh-xiaod-pet

use3346631993/dsh-xiaod-pet

Anime whale-boy in a maid outfit as a desktop pet for the DeepSeek Harness web GUI: four expressions follow the turn (thinking / success / failure), free dragging with remembered position, click-to-cycle, a bottom-right standee that reports each turn's token usage and think latency with its own balance bubble, a chat wallpaper, a liquid-glass composer, a cute persona that calls you 主人 with 喵~ style particles, and a single switch in Settings to turn the whole look off.

224 days agoJust for Fun
G

dsh-usd-brep

gitend/dsh-usd-brep

NURBS BRep solid modeling studio with natural-language input, live 3D viewport (measure/wireframe/fit), STEP export, and agent tools driving NVIDIA usd-brep through a managed CPython venv. Needs CPython 3.12; usd-brep wheels cover 64-bit Windows and Linux only.

221 days agoTools & CapabilitiesMIT
R

dsh-stats

rongyishuaige7/dsh-stats

Project-level usage hub for DSH: per-project token, time and cost, with half-hour swimlanes, 26-week activity heatmaps and provider balance alerts; unpriceable usage is flagged rather than estimated.

211 days agoUsage & BillingMIT
Q

dsh-lit-shot

qiaoschoco/dsh-lit-shot

Screenshot button for the DSH composer on Windows: drag a region over the frozen screen and the picture lands in the draft as a normal image attachment, with a global hotkey and an editable shortcut.

216 days agoUI EnhancementsMIT
I

dsh-assistant-profile

istarrydust/dsh-assistant-profile

Agent persona: gives DSH one global persona (name, language, persona prompt) that every new session carries at the front of its system prompt, plus a long-term memory you grow from any chat in one click; three built-in presets ship with it, and a Big fat fish persona is active right after install; chat sessions can also be deleted from the sidebar row menu.

27 days agoIntegrations & RemoteMIT