Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

4042 plugins found

X

dsh-research-suite

xuzhecomeon/dsh-research-suite

Research workflow suite that registers 10 domain skills and 15 tools, curates 450 bundled research skills into 103 capability cards with an auditable per-skill ledger, and takes over research requests automatically through a system-prompt section. Tools cover real R/Python execution (off by default, two-phase preview then confirm), data gates, figure and docx auditing, .docx generation in Chinese-journal style, live PubMed search, field-level DOI verification, and cross-session project memory.

23 days agoSkillsMIT
B

dsh-siyuan-sender

baby7/dsh-siyuan-sender

Sends a Markdown file from the conversation into a self-hosted SiYuan notebook: a button on every delivered-file card and on the document-preview toolbar, or just ask the agent to send it, all through the SiYuan kernel HTTP API. Existing notes are never overwritten — a repeated title gets a timestamp suffix — and the API token stays in the host credential store rather than in settings files or the browser.

28 days agoTools & CapabilitiesMIT
N

dsh-minimax-byapi

ningyuanlee/dsh-minimax-byapi

Native MiniMax provider for DeepSeek Harness: chat over the official MiniMax API, plus image, video, speech, music and transcription tools.

26 days agoModels & ProvidersMIT
J

dsh-linked-workspace

jiahui-huang1/dsh-linked-workspace

SSH-backed remote directories and linked local⇄remote workspaces: read-only remote browsing, an editable linked workbench, bidirectional SFTP transfer, mirroring and a linked_workspace tool. Sidebar pages require the dsh-better-sidebar plugin (v0.24+); without it only the Settings pages load.

2yesterdayIntegrations & RemoteMIT
F

dsh-wecom-soul-bot

flashpoint007/dsh-wecom-soul-bot

WeCom smart bot over the official long connection (Bot ID + Secret, no public callback): persona, sender identity tags, three-layer memory with a forgetting curve, reminders, opt-in proactive chat, owner-only work mode guarded by tools.guard, auto-steer, image input and a wecomSoulBot host service; group chats answer when @-mentioned.

213 days agoIntegrations & RemoteMIT
Z

dsh-plugin-book-deconstruct

zmz123612/dsh-plugin-book-deconstruct

Host plugin that adds the /dsh-plugin-book-deconstruct command and the dsh-plugin-book-deconstruct tool to any session for a full book walkthrough plus one deep insight.

29 days agoTools & CapabilitiesMIT
H

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.

213 days agoTools & CapabilitiesMIT
C

dsh-plugin-sessiongraph (bundle)

cc19990113/dsh-plugin-sessiongraph

Full-text search of all local sessions: sessiongraph finds conversations in any workspace, Chinese two-character terms included; sessiongraph_index builds it.

27 days agoSessions & MessagesMIT
Y

dsh-sidebar-groups

yangdinghui/dsh-sidebar-groups

Groups the sidebar's panel rows: two stay pinned, the rest fold under a collapsible Tools row, and rows can be dragged between the two groups.

25 days agoUI EnhancementsMIT
T

system-resource-monitor (dsh-hardware-monitor)

tyvtjhj/system-resource-monitor

Local hardware monitor for DSH: a sidebar dashboard, a composer-dock CPU/memory/GPU widget, and a hardware_monitor_status tool backed by a local Python service installed separately from the repository root with install-dsh.ps1 (Windows, Python 3.10); installing only the DSH plugin leaves the panel and tool offline.

213 days agoUI EnhancementsMIT
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.

213 days agoJust for FunMIT
C

dsh-gitlab-panel

caimc21069065-prog/dsh-gitlab-panel

GitLab panel in the DSH right sidebar: commit graph, branches, changes, merge requests (inline diffs, review submission, pipelines), issues, and agent tools with an approval queue for triage and batch actions. GitLab data needs a personal access token or a logged-in `glab`; local git data works without either.

217 days agoGit & Code Review
C

dsh-search-proxy

chaos-paradox/dsh-search-proxy

SearXNG web search with a managed local runtime, external instance support, Web settings, and an optional DSH process proxy.

220 days agoTools & CapabilitiesMIT
W

dsh-wsl-sidebar

wang1462604987/dsh-wsl-sidebar

WSL console for the harness — manage distributions, edit .wslconfig and wsl.conf in a typed form, and run commands, file edits and long-running processes inside any distribution with its own wslx-* tools.

25 days agoDev & Plugin ToolsMIT
R

what-sub-agents-doing-now

realoiyo/what-sub-agents-doing-now

Registers a read-only tool that lets a parent agent read what each subagent is actually doing, not just whether it is running: the progress notes the child wrote itself, oldest first, paged backwards by seq, plus how many steps passed since the last look, and a quiet count when five or more steps go by with no new note.

218 days agoTools & CapabilitiesMIT
I

dsh-tool-call-leak-fix

irwdone/dsh-tool-call-leak-fix

Blocks a tool call whose arguments lost their boundary, keeps a closing turn open when a step silently never ran so the model can re-issue it, and replaces damaged output on the model-visible surface after a fork. Zero dependencies.

25 days agoTools & CapabilitiesMIT
2

dsh-nx

27painter/dsh-nx

Drives Siemens NX 2406 and 2506 from DeepSeek Harness, plus NX 12: an executor that judges a journal run from its log rather than its exit code (NX returns 0 for a journal that swallowed its exception, and 0xC0000409 after a clean one), 16 typed tools over a resident batch NX, and a probe that keeps the three releases apart. Windows only; NX 2406 is the reference release, 2506 expected. Requires a local Siemens NX install and a free NX licence seat; run `dsh-nx install` once, and the 16 MCP tools stay off until `NX_ENABLE_MCP=1` is set (the skill route works without it).

2yesterdayTools & CapabilitiesMIT
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
N

dsh-jupyterlab

nkuhan123/dsh-jupyterlab

JupyterLab-style notebook for DSH: code and output side by side with a draggable divider, outputs that stick to the viewport while a long cell scrolls, Jupyter keyboard shortcuts (a/b/dd, m/y, Shift+Enter vs Ctrl+Enter), a scissors button to delete a cell and a chip to switch it between code and Markdown. Modified fork of @beihaizb/dsh-notebook: both register the same nb_* tools, so remove the original before installing; the Python kernel you pick needs ipykernel, jupyter_client and nbformat.

215 days agoUI EnhancementsMIT
L

dsh-artifacts

lucagiftzek/dsh-artifacts

An Artifacts tab in the DSH sidebar that lists the files an agent produced and previews them in place with live reload, plus artifact template tools for agents.

216 days agoUI EnhancementsMIT
S

dsh-mood

sata260/dsh-mood

Tracks an AI companion’s emotion and personality with a status panel, update tools, and chat stickers.

217 days agoJust for Fun
Y

dsh-rule-guard

yunling-bionic/dsh-rule-guard

Reviews side-effecting tool calls against the project rules and the current goal before they run, and denies anything out of scope with a fail-closed verdict and no bypass switch.

216 days agoSecurity & PermissionsMIT
X

elab-flow (dsh-elab-cockpit)

xkk6663/elab-flow

Embedded closed-loop development cockpit for DeepSeek Harness: the agent builds, flashes, debug-verifies and monitors STM32 boards from one panel, while the user watches every step live - progress ladder, streaming logs, RAM/FLASH usage and decoded serial waveforms. Requires a host Python 3.10+ on PATH (the plugin cannot install it); the ARM toolchain is auto-downloaded on first use (~400 MB, Windows x64 only), and you need an STM32 board with a debug probe.

29 days agoDev & Plugin ToolsApache-2.0
L

dsh-harness-autostart

lolitakawayi/dsh-harness-autostart

Adds one row to Settings → General with a switch that writes or removes a Windows logon startup entry for the DeepSeek Harness desktop app, and registers a dsh_autostart tool exposing the same status, enable and disable operations. Defaults to a single HKCU Run value, no admin rights; the startup-folder launcher mode adds an optional delay and launch arguments.

218 days agoDev & Plugin ToolsMIT