Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

33 plugins found

F

finsafe (windows)

finogeeks/finsafe

Windows sandbox for DSH Desktop: process isolation, permission controls, selected-file protection against accidental deletion, privacy and system security. FinShield limits reading, overwriting and deletion within configured protected files and directories. Privacy protection restricts screen capture and recording, camera and microphone access. System protection guards processes, services and registry settings, and limits desktop and input interference. Finogeeks has published 38 public comparison scenarios. Windows x64 only; install through the DSH Desktop plugin manager. First activation downloads and installs the matching native runtime with SHA256 verification and Windows consent, and runs an updater process. Protection depends on actual activation, configuration and version.

918 hours agoSecurity & Permissions
S

dsh-updater-npm

siriuswj/dsh-updater-npm

DSH updater + official docs sync in Settings: one-click npm update of @deepseek-ai/dsh with live progress (npm output stream, elapsed timer, monotonic bar), multi-copy protection that only touches the running instance, source-tree mode via git pull, one-click PowerShell 7 install on Windows, incremental sync of the official docs/ with progress, and the dsh_docs_search / dsh_docs_read model tools.

52 months agoDev & Plugin ToolsMIT
X

dsh-updater-ui

xingyingyuzhui/dsh-updater-ui

DSH self-updater in the settings page: one-click check/pull (`git pull --ff-only`), auto background checks, version diff and changelog preview with a red-dot reminder.

53 months agoDev & Plugin ToolsMIT
M

dsh-better-plugin-updater

mooling0602/dsh-better-plugin-updater

Update checker for plugin bundles installed in a DSH profile: a Version section on the detail page of a plugin installed from a GitHub repository or release tarball compares the installed commit or version with the exact target, and the /plugin-updater commands list bundles, check npm, Git-repository and GitHub-release sources, and prepare an update that runs only after confirmation; a read-only plugin_updates tool lets an agent check without installing, npm registry packages keep DSH native update controls, a fixed version or commit stays pinned unless explicitly allowed, and the plugin never approves build scripts.

26 days agoDev & Plugin ToolsMIT
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.

22 days agoModels & ProvidersMIT
C

dsh-plugin-suite (dsh-plugin-updater)

crtnt/dsh-plugin-suite

Update manager for installed plugins: check for updates, back up, and roll back.

23 months agoDev & Plugin ToolsMIT
M

dsh-app-controls

miraculousgu/dsh-app-controls

Adds quit and check/update controls to the DeepSeek Harness Web GUI, plus an optional KDE tray, per-feature settings, remembered window size, and safe cache cleanup.

113 hours agoUI EnhancementsMIT
Z

dsh-auto-update

zhkkjf/dsh-auto-update

Windows-only auto-updater for DSH Desktop: checks the official update feed, downloads and SHA-512 verifies the installer, then force-closes the app via a one-shot Task Scheduler job and installs silently (automatically by default), and after restart reinstalls profile plugins and restores their pre-update settings from a snapshot.

111 days agoDev & Plugin ToolsMIT
C

dsh-app-updater

ccgo26/dsh-app-updater

App Updater for DeepSeek Harness: detect every installed app that has a newer version and update it with one click by downloading the vendor's full installer from its official website and installing it silently — without launching the app. Windows (winget

115 days agoTools & CapabilitiesMIT
J

dsh-update-guard

jiuyuan-yi/dsh-update-guard

Checks installed plugins against a DSH update before you install it, and reports the shared UI members and host services they use that the new version no longer exports — the case where an update installs cleanly but leaves plugins failing to load. Includes a read-only diagnose command. Windows only, DSH desktop, Node.js 18+.

14 days agoDev & Plugin ToolsMIT
1

dsh-app-updater

19952730389/dsh-app-updater

Detect which installed apps have a newer version and update them with one click, downloading each vendor's full installer from its official site and installing it silently. Windows via winget, macOS via Homebrew casks, matching the machine's ARM64 or x64 architecture.

12 days agoTools & CapabilitiesMIT
M

dsh-updater

mutoharohfiqhiabcd-source/dsh-updater

在 DSH 里检测 / 回滚 / 查看版本,并管理 dsh 自动更新器(In-DSH check, rollback and version panel for the DSH updater)

126 days agoDev & Plugin Tools
Z

dsh-update-safe

zudazhuang/dsh-update-safe

Source-install updater for DeepSeek Harness: checks the official GitHub release and the npm record, builds the target tag in an isolated directory, smoke-starts it, then switches through a supervisor process with rollback, with scheduled checks and a daily idle-only install window. Source install only (macOS/Linux); requires Node.js 22.19+, pnpm and Git.

128 days agoDev & Plugin ToolsMIT
W

dsh-auto-update

wonderow666/dsh-auto-update

Windows only; the upgrade path needs DSH_AUTO_UPDATE_LAUNCH_CMD configured. Checks, installs and rolls back DeepSeek Harness CLI updates from the web settings page, switching the launcher pointer only after the new version passes a config-tree check and a health-checked restart, and reverting automatically when it does not boot.

128 days agoDev & Plugin ToolsMIT
N

dsh-autoupdater

niubi6668889595/dsh-autoupdater

Scheduled update checks for DeepSeek Harness itself and installed plugins, applied only in idle windows — four schedule modes (daily, every N hours/days/minutes), bidirectional plugin whitelist, disk-verified installs, and a web settings panel with hot-reload config.

124 days agoDev & Plugin ToolsMIT
S

dsh-check-for-updates

shanhaifish/dsh-check-for-updates

DSH 更新检查插件(静态 bundle):首次打开自动检查 DSH 新版本(取 npm 实际最高版本),左下方弹窗提示并提供【更新到】按钮自动执行已校验升级;UI 使用 DSH 语义化主题 token;DSH 安装根/版本、node/npm 均在运行时探测,无硬编码路径。

13 months agoDev & Plugin ToolsMIT
Z

dsh-web-update

zero-kq/dsh-web-update

Linux dsh web self-updater: checks npm at startup and every 24 hours, then installs the newer @deepseek-ai/dsh release and restarts dsh web by itself.

021 hours agoDev & Plugin ToolsMIT
F

dsh-plugins-update

fengzhiyushui/dsh-plugins-update

Update checker and installer companion for third-party DSH plugins with startup sidebar and row badges that reconcile after native updates, concurrent CDN checks and upgrades for GitHub branch/tag (#ref) and monorepo subpath specs, npm/npmmirror/custom registry switching with official fallback, minimumReleaseAge bypass, snapshot rollback with offline lockfile alignment, and an optional detail-page toggle.

04 days agoDev & Plugin ToolsMIT
Z

dsh-oneshot

zhangyong0010/dsh-oneshot

Plugin updater with an automatic parallel scan on opening its left-sidebar panel. Reuses the completed scan to skip current plugins without rechecking them and installs only confirmed newer targets. Checks DSH compatibility and installed versions, attempts recovery after failed GitHub updates, and shows one history card per operation. Includes a dsh_oneshot_update agent tool.

08 days agoDev & Plugin ToolsMIT
F

dsh-autoupdater

fangchenghao/dsh-autoupdater

Maintained fork of dsh-autoupdater with macOS/Windows desktop fixes. Scheduled update checks for DSH itself and installed plugins, applied only in idle windows.

023 days agoDev & Plugin ToolsMIT
L

dsh-plugin-steward

lihao178/dsh-plugin-steward

Plugin steward for DeepSeek-Harness: checks every installed plugin for newer versions and installs them, snapshots the profile first and rolls back automatically when the post-update health check regresses. Also scans plugin code for risky behaviour before you install (eval, reverse shell, credential access), browses the 8.5k-plugin catalog with compatibility badges, restarts the host by itself after install/uninstall/disable, and shows everything in plain language.

015 days agoDev & Plugin ToolsMIT
B

dsh-sync-updater

bertli486/dsh-sync-updater

Inventories installed DSH skills and profile plugins, checks their upstream sources for newer versions, applies the updates, and installs skills from a searchable catalog.

020 days agoDev & Plugin ToolsMIT
F

dsh-plugin-updater

feely0208/dsh-plugin-updater

检查并更新第三方 DSH 插件:对比 npm 最新版本,精确升级(绕过 pnpm 新版本观察期)。入口在「插件页 → 插件更新」标签页。

025 days agoDev & Plugin ToolsMIT
G

dsh-plugin-updater

gorkaseto/dsh-plugin-updater

Helps keeping tracked updates from plugins added from github with a simple usability UI.

024 days agoTools & CapabilitiesApache-2.0