Plugins
Browse, filter, and install DeepSeek-Harness plugins.
1073 plugins found
dsh-mesh
fishexploi/dsh-mesh
LAN task delegation between DSH hosts on one network: the parent dispatches a task to a child host, the child works in its own session and workspace, results and files return to the parent's inbox, sensitive actions wait for the parent's approval, and a finished task can be continued with one follow-up inside the child's existing session. Since 0.4.0 a fresh host listens on loopback only and keeps its listener off until it is enabled, the six-digit pairing code is single-use and rotates with a lockout after repeated failures, tokens travel in an Authorization header and are stored hashed, and a dispatch with no grant or with a permission above the grant is refused before anything is sent. Transport is still plain HTTP with no TLS, so use it on a trusted LAN.
dsh-dafeiyu-emotion
lidu-china/dsh-dafeiyu-emotion
Adds a fish-ear microphone to DSH that transcribes speech locally, estimates tone and emotion, and lets BigFish reply with an emotion-aware prompt.
dsh-qq-zone
lfelkeea/dsh-qq-zone
Publishes and reads QQ Zone posts through SnowLuma's OneBot qzone_* actions (SnowLuma 2.2+ signed in to QQ), and lets the agent understand images with a local vision model (OpenAI-compatible gateway) or Windows OCR.
dsh-hierarchical-fishmemory
marsstorm/dsh-hierarchical-fishmemory
Layered long-term memory for DeepSeek Harness - a merge of AirPineApplea/feiyu-memory 4.0.2, dsh-soul-md and dsh-shallow-memory (do not install it alongside those plugins): a diary distilled from finished turns, a hand-written feelings diary, a persona card with version history, a hand-note injected in full every turn, and a short-TTL note layer, each capped separately so per-turn injection stays small; ships agent tools and a sidebar panel for recall, editing, compaction, and backup or restore from a local file, WebDAV or a gzip archive.
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-shark-bg
iemgnod/dsh-shark-bg
ASCII sharks and schooling fish swim behind the DSH Web interface, with a settings page for veil opacity, shark count, size, fish density, swim speed and grid strength.
dsh-qq-sounds
gexiubinhelloworld/dsh-qq-sounds
QQ-style alert sounds for DSH: the QQ message tone when a turn finishes and the QQ system tone when approval or an answer is needed, reading your local QQ install on Windows and falling back to built-in tones.
xander-zaozao-xiaban
gx18391303625-afk/xander-zaozao-xiaban
Xander Amazon seller-operations toolkit for DeepSeek Harness: 33 native xander_* tools and 7 skills for competitor research, keywords, listings, ads, replenishment and profit, with exact proposals, explicit approval and read-back verification for Amazon changes.
dsh-scratch-workspace
s0meb0dy3/dsh-scratch-workspace
Creates a throwaway workspace with its own folder and session, manages running ones from a sidebar panel, and moves finished folders to the system Trash.
dsh-lark-agent
nirvana-jie/dsh-lark-agent
Reach your DeepSeek Harness assistant from Feishu / Lark: a dsh plugin built on the official Lark CLI
dsh-novel-fish
gongfpp/dsh-novel-fish
Read local EPUB, TXT and Markdown novels below selected native DSH chat regions on explicit expansion, preserving real reasoning and tool output without sending novel text to the model. Requires DSH >=0.2.1-rc.2 <0.3.0-0.
dsh-flymemory
aujurd22/dsh-flymemory
Structural long-term memory for DSH: supersede, decay and entity-state tracking across 15 MCP tools, automatic recall and capture hooks, and a bounded pointer index published per request instead of filling the window. Requires Python 3.10+ with torch and sentence-transformers; the first run downloads a ~470 MB embedding model.
dsh-plugin-upgrader
zuwenyin/dsh-plugin-upgrader
A Versions tab on the Plugins page: one-click upgrades that replace the plugin in place where they can (no uninstall, enabled state preserved, falling back to remove + reinstall with the reason logged when the profile writer lock is busy), live pnpm output with per-step timing and cancel, the full published version history with one-click rollback, every version checked against the running DSH so incompatible ones are marked and blocked, a rollback that installs the old version but cannot activate it reported separately from a lost package, profile manifest writes taken under the harness writer lock with one recoverable journal record per package after a failed upgrade, mirror-gap warnings, and a selectable npm registry saved in the profile.
dsh-im-union
drscrewdriver/dsh-im-union
Union IM bridge for DSH — an independent implementation uniting the capability sets of community peer plugins (xmanrui/dsh-im, MichengAI/dsh-im-connect). Drive your agent session from 15 channel adapters across 12 platforms (including email; WeCom/DingTalk/QQ each contribute two: bot + self-built app or notify tier) — WeChat (official iLink QR bind), Feishu/Lark (long-connection + streaming cards; the voice tier requires system ffmpeg), Telegram, Discord, WeCom intelligent bot & self-built app (signed callback), DingTalk (stream + AI Card and custom-robot notify), QQ official bot (plus notify tier), Slack (Socket Mode), WhatsApp (Baileys QR pairing; the dependency ships as an optionalDependency of the plugin package), Matrix, iMessage (macOS only), Email (IMAP/SMTP thread routing). The cross-version narrow waist auto-adapts settings gen1/gen2/gen3 across hosts 0.1.2-rc.1→0.2.1-rc.2 (12-tag enum; rc.2 verified by a real desktop-profile install with double read-back) using capability probing only, never version branches. In chat: a 25-command panel, tool-approval and question loops answered in the originating chat (deny-by-default, initiator-only, 5-min expiry), image/file input gated on host model metadata, deliverable file return, a delivery log with bounded retry (uncertain is never re-sent), proactive delivery and fragment composition. It also splits the native sidebar into self-owned Tasks / Channels tabs (standing down entirely when another plugin already owns the slot), registers an `im-concise` agent preset plus reply sanitisation that keeps GenUI fences and raw HTML out of text-only chats, renders `svg` fences to PNG images, guards model choice with an allowlist, and mirrors each turn's final answer to notify channels via `/relay` (addressed by account ID or alias, never guessed on ambiguity). Secrets are one-way into the vault and never echoed back. npm: `dsh-im-union`.
dsh-wechat-media
wjh-ux/dsh-wechat-media
Personal WeChat and WeCom (企业微信) bridge: QR pairing, one DSH conversation per chat, two-way text/image/video/document/archive transfer, chat commands (/help, /status, /new, /stop, /friends) answered by the bridge itself without spending a model turn, a switch that restricts the bot to 1:1 chats (group messages are dropped silently and counted), remote approval by replying 1 or 2 in the chat, and a two-way WeCom intelligent robot over its long connection (no public URL needed) that also receives and sends images, files and videos.
dsh-notify-say
unifilitence/dsh-notify-say
Windows desktop notifications for DSH that speak the turn result by default: Windows TTS needs no download, and 13 VOICEVOX voice packs can be installed from the settings page. A completed alert waits until running subagents and background jobs finish; approval, question and error alerts fire immediately. Voice packs are downloaded from GitHub after a terms confirmation.
dsh-scholar-suite
docsor1212/dsh-scholar-suite
Eight academic skills bundled for one-command install — publication-ready academic figures designed from real data with visual review, AI-text humanization, paper polishing and rewriting, PubMed citation verification (DOI/PMID reconciliation), Chinese citation and medical-book reference checks, and WeChat medical article structuring. Three skills run fully local, five call external services only when used (NCBI E-utilities, DOI resolvers, publishing platforms), declared per skill. Zero telemetry, no install-time scripts. Skills run local Python 3.8+; the academic-figures skill also needs its pip dependencies installed.
dsh-douyin-subagent
wu079/dsh-douyin-subagent
Runs a Douyin subagent that browses videos and reads comments in valley hours and reports back, with dy_* tools for publishing and replying (comments sent from the already-logged-in page with its own request signature, no IM ticket), a daily quota timer, and a settings panel under Settings → Douyin: master switch, auto mode, valley windows, rounds per day and report depth. Windows-oriented; needs the separate douyin-mcp binary (yunsur/douyin-mcp releases, path set via dy_config mcpExe) and an Edge/Chromium login; replying needs a logged-in browser on a CDP port; publishing needs extra credentials most accounts lack.
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-workbuddy-harness
bushizhanghan/dsh-workbuddy-harness
Brings WorkBuddy free/paid models (domestic + international) into DSH without the desktop app, published as @bushizhanghan/dsh-workmate. This package is a maintained fork of Faide-cyber/dsh-workbuddy (whose upstream entry is already listed in this catalogue); do NOT co-install both, as they register the same provider id "workbuddy-ai" and will collide. v1.2.7 relocates over-long system prompts past the domestic gateway channel-risk classifier, rewrites the DSH brand string, and adds a debug dump; supports dsh 0.2.0-rc.2 through 0.2.1 (incl. prereleases).
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-pharos
leo-cjw/dsh-pharos
Desktop notifications for DSH: a system toast, a per-kind chime and a tab-title marker when the agent needs you (approval, plan review, question) or a reply finishes in the background; errors, interrupts, usage limits and multi-agent workflow progress alert too. A host half adds SSE delivery, webhook push (WeCom/Feishu/DingTalk/generic), per-turn token/cache/TPS stats, plus three message-format presets (concise, detailed, custom); settings changes auto-save.
dsh-commandcode-goat
plocr/dsh-commandcode-goat
Command Code subscription tiers (Go / GOAT / Pro / Max) published as `llm-pi-ai` route profiles rather than an adapter: the live /provider/v1/models list and the plan page capability catalog are joined, each model lands on the OpenAI Chat, OpenAI Responses or Anthropic Messages route the gateway's own supported endpoints call for, switching tier deletes the routes the previous one generated, and the same credential drives five-hour and weekly usage windows, credit balances and a web-search provider.
dsh-lark-plus
anfruj/dsh-lark-plus
DeepSeek Harness × Feishu/Lark bridge: chat, cards, approvals, task board, goals and schedules in Feishu — plus fully local (offline) voice transcription with a play bar in the Web GUI.