Plugins
Browse, filter, and install DeepSeek-Harness plugins.
163 plugins found
dsh-wechat-bridge
lanbaolu/dsh-wechat-bridge
Two-way WeChat bridge for DeepSeek Harness via the iLink protocol: bind your personal WeChat with a QR scan and chat with a local DSH agent from the chat box (text, images, voice-to-text, files); a web settings panel handles binding/start/stop/status, project-session binding continues the conversation on desktop, proactive wechat_notify pushes include throttling, and the pure-Node daemon runs on Windows/macOS/Linux.
dsh-session-popout
lumine-423/dsh-session-popout
Drag a session out of the DSH sidebar and it opens in its own native OS window, showing the full standard conversation UI (Markdown, toolbar, settings) with only the sidebar trimmed away, so several sessions can be watched side by side instead of switching back and forth. Windows verified; macOS and Linux untested. Runs in the DSH desktop app (Electron).
dsh-rate-limiter
xidong-ai/dsh-rate-limiter
Proactive per-provider token-bucket rate limiting that queues over-limit requests before they are sent, preventing upstream 429 errors.
dsh-chrome-bridge
orderg-x/dsh-chrome-bridge
DSH plugin: native browser_* tools that drive the Chrome you are already using, over native messaging + CDP. No WebSocket, no port, no Connect button. The native host and the MV3 extension ship inside this package and are installed automatically on first
dsh-on-phone
jaulukngai/dsh-on-phone
Puts the DSH web UI on a phone browser over your own tailnet, with the remote channel built on Tailscale Serve. Both sides need only Tailscale: no dedicated app, no QR code, no login page, no account of its own, and no relay of your content. The desktop half runs on macOS, Windows or Linux.
dsh-desktop-notify
mvyvn/dsh-desktop-notify
Notifies you about 11 configurable DSH agent events (task completion, questions, denied approvals, background subagents/goals/jobs, team tasks, context compaction, triggered schedules, plugin startup and permission changes) as browser Web Notifications through a bundled service worker, falling back to Windows toast or Linux D-Bus, with three silence levels and click-to-open.
dsh-wsl-native
han-1413141/dsh-wsl-native
Use Windows and native Linux DSH sessions in one Windows window, with WSL environment switching and bidirectional system tools.
dsh-native-browser
longmiaoo/dsh-native-browser
Browser plugin for DSH (浏览器): Codex-style native browser control in your signed-in Chrome, with smooth virtual-cursor feedback, semantic page reads, form filling, screenshots and handoff; setup from the Browser sidebar. Requires macOS + Google Chrome (Chrome 125+) and a one-time unpacked load of the bundled MV3 extension; Edge, Windows and complete Linux installation are experimental.
dsh-plugin-tomato-todo (plugin)
anthealaffy/dsh-plugin-tomato-todo
Pomodoro timer, tasks and study planning in DSH, with a chat assistant that can read and update the same local records as the UI. Needs the separate tomato-runtime service (Linux release bundle from the project) running on 127.0.0.1:43987.
dsh-wsl-suite
stallenlu/dsh-wsl-suite
WSL workspaces for DeepSeek Harness. A sidebar W button lists installed distros and registers a Linux folder as a host workspace addressed by a UNC path, and the sidebar terminal opens a real Linux pty inside the distribution for WSL sessions. A persistent zero-dependency agent running in the distro answers file, shell and search requests over a JSON-lines pipe, so no polling timers touch the distribution while it is idle and /mnt drives stay reachable from tools and the terminal (registering one as a workspace is refused, because the host realpaths workspace paths and Windows cannot resolve drvfs); grep and glob run the distro's own ripgrep. WSL preset twins such as wsl-standard swap in the WSL shell and fs tools. A rebuild of 6Mikao9/dsh-wsl-workspace — do not install both: they mount the same W entry in the Workspaces header, publish the same wsl-<mode> presets, and each wrap the host's single-slot terminal provider.
office-ppt
pawpress/office-ppt
Builds presentations by driving the LibreOffice installed on the machine over UNO instead of writing OOXML in JavaScript: `lo_build` opens a real Impress document from structured slides and lets LibreOffice export editable PPTX/ODP plus PDF and per-slide PNG, `lo_render` re-renders an existing PPTX/PPT/ODP, `lo_convert` converts between Office formats, `lo_probe` reports the detected soffice path, version and UNO bridge, and `lo_config` edits the stored settings. Needs a local LibreOffice (verified on 26.8.1.1); it uses the bundled Python, so no system Python is needed, and it keeps one warm soffice process between calls. Fully verified on Windows only; on Linux it falls back to the system python3, which needs python3-uno.
dsh-refresh-restart
hulibuld/dsh-refresh-restart
Adds two buttons beside the sidebar toggle at the top-left of the DSH desktop UI, on macOS, Windows and Linux. Reload refreshes only the UI layer while a turn already generating keeps running; restart asks for one confirmation, quits the whole app and reopens it with sessions and workspaces intact. Restart is a POST that must carry a random per-boot token read from the plugin's status route. The plugin makes no network calls, reads no session content and has zero runtime dependencies.
dsh-wsl-bridge
tgwgulugu/dsh-wsl-bridge
Runs persistent bash and Linux-path file and search tools inside the current WSL distribution. A new conversation that selects WSL mode asks which of that distribution's folders to use as the workspace, and nothing is installed inside the distribution.
dsh-kujira-persona
tests4gptplay/dsh-kujira-persona
Model-linked characters and a shared world for DSH, with separate editable personas and memories, optional AI diaries and sleep consolidation, Chinese/English controls, task-aware desktop pets, themes and usage statistics; updates preserve user customizations. Supports Windows, Linux and macOS; see the guide for each system's installation requirements. Diaries and consolidation consume tokens. Before installing or updating, we recommend closing visible desktop pets and bubbles; open files may cause installation to fail. Codex and OpenAI API account queries have been user-validated; other sources await user validation and feedback.
dsh-connect-cursor
greatyao/dsh-connect-cursor
Connects a locally-signed-in Cursor desktop app to dsh as a native LlmAdapter — reads the Cursor login token from state.vscdb or auth.json, drives the private agent.v1.AgentService/Run HTTP/2 bidi stream, and translates InteractionUpdate deltas into dsh StreamChunks. No loopback proxy. macOS, Windows and Linux.
dsh-minato
sakanamaru/dsh-minato
Optional read-only bridge plugin that publishes live dsh session and token statistics as one JSON snapshot for the standalone dsh-minato toolkit to read.
dsh-wsl-open
173787247/dsh-wsl-open
Opens WSL Linux paths from DeepSeek Harness chat in the Windows default app or Explorer.
dsh-wsl-env
173787247/dsh-wsl-env
Injects WSL distro, Linux path mapping, /mnt/c CRLF and git caveats, and NODE_USE_ENV_PROXY into the system prompt.
apk-reverse-skill
xiaotianya14/apk-reverse-skill
Mobile-first Android APK reverse-engineering skill for DSH — decode with jadx/apktool, locate ad SDKs and entitlement logic, patch smali or values, repack/align/sign, then verify on a real device. Installs the apk-reverse skill; all tooling runs locally in proot Ubuntu on the phone or on PC Linux.
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-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.
dsh-notes-plugin
zxy0902/dsh-notes-plugin
Notes and folder reader in the main panel: a file tree with pinned files, closeable tabs, Markdown split edit/preview with synced scrolling, plain-text editing, manual save, and drag-to-move. Deleting a file moves it to the system trash where one exists (macOS, Linux), falling back to an in-folder dsh-notes-trash directory; Windows has no delete entry.
dsh-autorestart
eason-22/dsh-autorestart
DeepSeek Harness plugin: restart without losing work. It waits until every conversation is idle, restarts the host, and picks the interrupted work back up instead of dying with it; where a supervisor already manages the host it asks that supervisor, and it never starts a second host next to a running one. It also fixes a common one: stale login cookies pile up on every launch until the request header overflows and the host will not start; the plugin clears them before each restart. Every restart is preceded by a snapshot of the configuration and the installed plugins - 2 are kept by default, up to 10 are allowed, and old or incomplete ones are pruned. That snapshot is never applied automatically: the plugin does not watch the host and does not restore anything on its own; it is only there for you to look at, or to roll back by hand. When the work is done it counts down and powers the machine off, so nobody has to stay up at night. It works on the Windows desktop client, and on a hosted dsh web instance - verified on WSL with systemd; Windows-hosted web, WSL without systemd, and native Linux are untested.
dsh-cloud-workspaces
harryopo/dsh-cloud-workspaces
Cloud workspaces for DeepSeek Harness: pick "Cloud (SSH)" in the workspace chooser and the agent's bash/read/write/edit/glob/grep tools transparently run on your Linux server over SSH. Includes ssh_* agent tools, an SSH host settings card, jump-host suppo