Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

544 plugins found

A

dsh-github-router

angeloszou/dsh-github-router

Read-only GitHub access for agents, wrapping several tools. Inside the tool it automatically probes and selects whichever GitHub access method works locally, and tries network proxies on its own. That cuts down the network and parsing problems an agent may hit when accessing GitHub, and the overhead of it repeatedly trying different approaches.

32 months agoGit & Code ReviewMIT
V

dsh-shutdown-after-task

virggle/dsh-shutdown-after-task

Shut down Windows automatically after DeepSeek Harness tasks complete — a floating arm button plus a cancellable countdown banner (shutdown /a), zero runtime dependencies.

33 months agoWorkflow & AutomationMIT
H

dsh-vision-mix

haiziyao/dsh-vision-mix

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

32 months agoVision, Voice & MultimodalMIT
R

dsh-wallpaper-engine

ruijiaang-lab/dsh-wallpaper-engine

Wallpaper backgrounds for the DSH web GUI. Windows: reads your Wallpaper Engine (Steam) library and plays video/web wallpapers behind the chat. macOS: scans the WaifuX download folder and loose media folders automatically — anything saved in WaifuX becomes a DSH background with zero setup. Liquid-glass blur, dim and border sliders.

32 months agoThemes & Appearance
Y

dsh-token-usage-sidebar

y2zyyr/dsh-token-usage-sidebar

Persistent local token-usage accounting for DSH Web with automatic history discovery and compact provider/model details.

32 months agoUsage & BillingMIT
F

dsh-plugin-llm-balance

fenghuolinshan/dsh-plugin-llm-balance

DSH balance and quota card showing up to 3 recently used providers. Supports DeepSeek, Moonshot, Kimi For Coding, OpenAI Codex, and OpenCode Go, with auto-discovery, quota windows, reset times, color-coded status, dragging, and automatic refresh.

32 months agoUsage & BillingMIT
J

dsh-polyglot

jesse-njx/dsh-polyglot

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

33 months agoModels & ProvidersMIT
Y

deepseek-heartflow

yun520-1/deepseek-heartflow

HeartFlow (心虫) AGI layer-1 discriminator gate as a DSH plugin: 47-dimension rule-based text checking (heartflow_check tool) plus automatic output supervision at tools/post-execute, fail-closed when engine missing.

33 months agoTools & CapabilitiesMIT
J

dsh-memoria

jiayan-xu/dsh-memoria

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with automatic turn-end persistence and per-agent namespace isolation.

33 months agoMemoryBSD-3-Clause
D

dsh-novel-fade

drizzlegig/dsh-novel-fade

Writing a novel of hundreds of thousands, even millions, of words with AI — but always worried it will forget earlier plot, characters and foreshadowing? Loading piles of old chapters into the context every time is not only costly; it also crowds out the room that should go to actual creation. Fade gives the AI a long-form memory that gradually fades: the recent plot stays sharp, the distant story keeps its key points, and important characters and events can be recalled whenever needed. When a chapter is finished, its memory is organized and its text archived automatically — no need to carry the whole novel around. Cut unnecessary token consumption, keep more context and budget for the chapters ahead, and let AI help you write a longer story.

23 days agoMemoryMIT
D

oh-my-clm

devzjqx/oh-my-clm

Pi extension + DSH plugin: manual live-context cleanup and automatic, replay-safe tool-result clearing.

23 days agoSessions & MessagesMIT
Z

dsh-excalidraw-canvas

zhiyaunhe-ops/dsh-excalidraw-canvas

Excalidraw workspaces for local DSH Desktop or a separately deployed cloud server, with automatic saving and document-scoped assistant sessions. Requires workspace setup.

23 days agoTools & CapabilitiesMIT
C

voice-call

crease123/voice-call

Start with the author tutorial: https://www.bilibili.com/video/BV1t9sJ6NErV/ . Talk to your current DSH Agent without switching presets: automatic speech transcription and sending, streamed spoken replies, voice interruption, and a five-bar microphone meter. Choose DeepSeek or Doubao independently for ASR and TTS, configure your own credentials, and edit instructions applied only during calls. Includes a Bilibili usage tutorial, phone-button screenshots, and a Restore defaults action for call instructions.

24 days agoVision, Voice & MultimodalMIT
J

dsh-code-review

jkin8010/dsh-code-review

Code review center for DSH, built on open-code-review: reviews current changes, commits, branch ranges, project architecture, code modules and business data flows, with live progress, a GitHub-style commit heatmap, fixed markers, automatic fix verification, light/dark themes and one-click fix sessions. Needs git; AI review also needs the open-code-review CLI 1.13 or later (npm i -g @alibaba-group/open-code-review), and the reviewed code goes to that CLI's configured LLM, or to the session model when the review is delegated to it. The engine is picked automatically — that CLI's model, then the session model, then offline structural analysis — so findings still come back with no API key; reopening a report after a fix session re-runs the review to verify the fixes.

24 days agoDev & Plugin ToolsApache-2.0
Z

dsh-xiaoyu-qqbot

zottall/dsh-xiaoyu-qqbot

QQ-bot console for DeepSeek Harness on Windows, with NapCat/AstrBot deployment, GPT-SoVITS integration, persona editing, local hybrid memory retrieval and a 3D memory graph. The services do not start automatically, and strangers get no tool access by default. QQ messages reach DSH through the third-party AstrBot (astrbot_plugin_dsh) and dsh-astrbot-ingress, both deployed from pinned sources.

29 days agoIntegrations & Remote
A

dsh-subagent-switch

ashenseeker/dsh-subagent-switch

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

213 days agoModels & ProvidersMIT
C

dsh-paper-workbench (dsh-paper-workbench)

cluodwaters/dsh-paper-workbench

A local literature workbench for Windows x64 with PDF reading and annotations, automatic initial reading, separate per-paper Harness conversations, and a library assistant that searches metadata and shared summaries.

2yesterdayTools & CapabilitiesAGPL-3.0
C

dsh-big-fish-speak

chaowei08/dsh-big-fish-speak

Makes the dsh-pet desktop pet read model replies aloud in its own configured voice. Newer dsh-pet gets the whole text in one request (up to its 500-char cap); older versions automatically fall back to 60-char chunks. Each piece is verified against the pet log to confirm it actually played.

27 days agoVision, Voice & MultimodalMIT
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.

24 days agoSkillsMIT
L

dsh-delivery-kit

lucky020/dsh-delivery-kit

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

220 days agoTools & CapabilitiesMIT
S

dsh-tri-model

starry-sky-blip/dsh-tri-model

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

215 days agoModels & ProvidersMIT
L

dsh-local-trim

leonlee114514/dsh-local-trim

One-step local model onboarding plus a light harness for DSH. On load it probes loopback and private-network inference endpoints (llama.cpp, Ollama, vLLM, LM Studio), reads each model's context window and output budget from the backend, and registers the provider through settings, so a local model becomes selectable without hand-writing config. It then trims only that provider: masks the tool list through tools.restrict, drops named system-prompt sections and memory contexts, swaps the injected instruction block for a short one while preserving its first 80 and last 96 characters, and truncates tool-schema descriptions without touching structure or required fields. Cloud providers are returned as the same assembly object, untouched. The injected block is re-read from disk on every assembly, so editing the file takes effect on the next request with no reload. The panel in the plugin detail page is a live operations view: it shows whether the takeover is active and by which hook, how many characters the last assembly was trimmed from and to, and which providers are online (probed concurrently, with a real one-shot completion reporting latency and reply text per provider). If a local backend is not running, the panel offers a one-click launch: it probes the port first (never starting a duplicate), then starts the matching server (ollama serve, or a custom command you supply) detached and polls until the endpoint answers, clamping the wait to 3-600 seconds, reaping the child it just spawned if it never answers, and naming the paths it searched when it cannot find the binary. A stop button kills backends this plugin started (SIGTERM, then SIGKILL) and refuses to touch a server somebody else launched. When a model has just been downloaded and no backend exists yet, the panel can also scan the machine for .gguf files with hard caps (300 models, 20000 directory entries, Downloads only one level deep), start llama-server on the chosen one (skipping the .mmproj. vision projection and reusing a server that already answers), register the provider under the model id the backend reports, and run one real completion to prove it works. Before spawning anything it does a fit check that counts only the part of the file the GPU cannot hold: hostBytes = fileSize - VRAM, compared against max(total RAM - 2GB, free RAM). A file far larger than RAM is refused outright; a heavy host-side remainder is refused unless you confirm; the same remainder under mmap is only a warning, because the weights land in reclaimable page cache. A load-mode selector (auto / mmap / none / mlock / mmap+mlock) maps to llama.cpp --load-mode, and the default is whatever the engine picks. From 0.4.2 everything above is derived from the platform instead of assumed: home and data directories come from os.homedir() and the OS conventions (LOCALAPPDATA on Windows, ~/Library/Application Support on macOS, XDG_DATA_HOME elsewhere); backend binaries are looked up in the official install locations of each OS and can be pinned with OLLAMA_BIN, LLAMA_SERVER_BIN, VLLM_BIN or LMSTUDIO_BIN; model discovery walks DSH_LOCAL_MODELS_DIR, ~/models, ~/llama.cpp/models, ~/.cache/llama.cpp and the LM Studio data directory, with the WorkBuddy layout demoted to one candidate among them. VRAM is asked from nvidia-smi, then rocm-smi, then sysctl hw.memsize on Apple Silicon (flagged unified, so the same bytes are not charged twice), and any flip to a unified-memory budget is handled explicitly. Before building a command line the plugin runs llama-server --help once and keeps only the flags that build actually has, so older engines get --n-gpu-layers 99 and no KV quantization while newer ones get auto plus q8_0; anything it cannot probe is passed through rather than dropped. LM Studio is started with lms server start --port N rather than being lumped in with the engines that need a model argument, and vLLM gets its own --model example instead of llama.cpp syntax. Windows, macOS and Linux are all exercised in CI, including a windows-latest and a macos-latest job, because a cross-platform claim that has only ever run on one OS is not a claim. Two of those suites exist specifically to catch this machine's blind spots: one replays the whole suite with process.platform rewritten to each OS, and one deletes every advantage this development box has — no nvidia-smi, no rocm-smi, no sysctl, an empty PATH, a home directory with no models — and requires graceful degradation rather than a crash. That last one caught a real class of bug: several assertions hardcoded 'lms.exe', which cannot pass where the executable has no suffix. Measured on the reference machine: a 16.9GB 27.2B MoE with 14.5GB of VRAM holds a 285-691MB working set and sustains 76 tok/s after a 1000-2000 token warm-up, so file size alone is not a fit signal. From 0.4.3 the scanned models are shown as a table rather than a dropdown (one row per gguf, with its size and any fit warning), so you can see what is on disk before choosing. From 0.4.4 the delete button on the provider table removes the provider entry, not the weights file on disk. That distinction matters: what people actually want to clear out is the dead entry - one pointing at a port that never answered, one registered twice for the same port, one whose model file was deleted long ago - not a 15.8GB gguf. Deleting a config is undone by importing again; deleting a gguf is not. The removal goes through settings.mutate with an unset op on \['providers', id], because update merges layers: writing null there leaves a null provider key that the loader reads as a broken config rather than an absent entry, and only mutate/unset is implemented as Reflect.deleteProperty. The result is read back afterwards, because unset on a key that comes from a lower layer (the profile cordis.patch.yml or a home patch) does not delete it - it restores the inherited value, so the call succeeds while the entry stays. When the entry is still there the panel says so and points at the file to edit instead of reporting success, and a DSH whose settings service predates mutate() is told plainly rather than silently ignored. Deleting takes two clicks and clearing the confirmation is as easy as clicking another row; on success the online and baseURL caches are cleared and the tool surface is recomputed, since the provider list changed. The gguf itself is never touched by this plugin - the scanned-model table is display and selection only.VRAM reporting is driver-dependent. From 0.4.5 model discovery also reads Ollama's own storage: its blobs are named sha256-… with no extension, so extension matching could never list them. Weights are now accepted by extension OR by GGUF magic header (only dot-free files of at least 8MB, capped at 600 header reads per scan; obviously-not-weights extensions like .json/.md/.safetensors/.part are never opened). Ollama models are resolved from their manifests: the model layer is picked by mediaType application/vnd.ollama.image.model (never adapter/mmproj layers), the human-readable name is restored from the manifest path (…/qwen3/8b becomes qwen3:8b, …/latest stays bare), tags sharing one blob merge into a single row, and the metadata kv supplies name, quantization and context length. Adopting an Ollama model does not start a duplicate llama-server over the same weights: it confirms ollama serve answers on 11434 (launching it if not) and registers the provider under the tag the endpoint itself reports — the blob's sha256 name would never match anything, since 11434 lists qwen3:14b, not sha256-a8cc…. Two real-machine-only traps fixed on the way: existsSync('<file>/') returns true on Windows, so manifest-vs-directory branching now goes by parseable content instead of trailing-slash semantics; and the quantization label table had been copied from a stale ggml enum generation, labelling ggml_type 15 as Q5_K_S while ollama show reports Q4_K_M. Same-blob dedup is by (dev,ino), keeping whichever entry has a name. Verified on the reference machine: the scan goes from 1 row to 4 — qwen3:14b (8.64G) and qwen3:8b (4.87G) now appear with Q4_K_M badges — in 4ms; npm run verify exits 0 (launcher 57, portable 35, panel-host green including the linux/darwin simulated-platform runs); the new panel-host suite builds a real miniature Ollama store in tmpdir and points OLLAMA_MODELS at it, so results no longer depend on whether the test machine happens to have Ollama installed. From 0.4.6 the panel shows each model its real name instead of its file name, because some download tooling stores every weight under one generic file name, leaving the real name only inside the GGUF header. The scan now reads each file GGUF KV section - not a fixed-size head buffer, because tokenizer.ggml.tokens (hundreds of thousands of strings on a large MoE model) and the chat template push general.file_type past any window; and GGUF string arrays are interleaved (u64 length plus payload per element), so treating them as a length table walks the cursor off the rails and produces astronomically large reads. Reading and skipping are accounted separately: key names and types are always read, string values over 256KB and string arrays are only walked past without copying, non-string arrays over 64 elements are skipped outright, and a cursor past the file size stops the read, because an out-of-range position means the cursor is wrong rather than that a limit should be raised. The displayed name goes Ollama tag, then general.basename plus size_label, then general.name, then the file name, with the full string kept for the hover text since it usually carries internal build numbers; mmproj files are now identified by general.type as well as by name. A short read (truncated file) no longer feeds half a value into the parser. On the reference machine, reading one file header parses 44 keys in about 16ms, and a whole scan takes about 31ms. From 0.4.7 the smoke test no longer fails the first time and passes the second. The old code gave both request attempts one shared AbortController and one shared 30-second timer, so the total budget covered both rounds: a cold load of a large model burned it in round one, the abort left the signal permanently aborted, and the second round (the Ollama-style reasoning_effort: none retry) could not even be sent - which is exactly why the first click returned This operation was aborted and the second succeeded. Now each attempt gets its own controller and timer, a timeout retries once automatically (retryOnTimeout, on by default) because a first-request timeout almost always means the weights are still being read from disk, and non-timeout errors (refused connection, HTTP error) are not retried at all. Timeouts report themselves: the message says the wait exceeded smokeTimeout, whether a retry already happened, and points at the new smokeTimeout setting (seconds, default 60, clamped to 5-600) - port responding is not the same as tokens coming out, so it is a separate knob from launchTimeout. Unrelated: an example naming one specific model was dropped from the panel copy, since not every machine has that model downloaded, and the explanation now describes the mechanism instead. From 0.4.8 adopting a plain .gguf no longer registers an unrelated Ollama model. The port field used to follow the last click rather than the file: selecting an Ollama entry moved it to 11434, selecting a plain .gguf did not move it back, so a 11434 left over from an earlier click stayed. The server accepted it as given, probed the port, found Ollama answering and borrowed it (the skipped-launch log line about the port already answering is this path), and then the model id - derived from the file name - could not be matched against Ollama's /v1/models, where the fallback was to grab the first entry in the list. Embedding models tend to sort first, so the adopt registered a model the user never selected. Now the port follows the file: a plain .gguf landing on another engine's port (ollama 11434, vLLM 8000, LM Studio 1234) is moved to 8090 and the panel says so. Only ports belonging to a known engine are overridden - a hand-typed 9999 aimed at your own llama-server is left alone. The model-id fallback no longer guesses either: it takes the only entry when there is exactly one (a single-model backend may legitimately report a different id than the file name) and otherwise reports an error listing the ids it did see, rather than registering a wrong provider. From 0.4.9 the panel can no longer vanish. It used to be possible for the whole section to disappear from the plugin detail page while the host stayed up, the HTTP bridge kept answering, and no crash log appeared. The cause was a scope error: a helper was declared inside one component and referenced from another, which is valid JavaScript and passes a syntax check, so it only threw at render time - when the user pressed the scan button and React ran the state updater. The host wraps every slot entry in an error boundary whose fallback is an empty anchor, so the throw was contained silently: the panel was not uninstalled or crashed, it was replaced by an empty div. The helpers now live in the module scope both components share. The client half also gained its own test - a minimal React stand-in loads the real panel module, really calls the components, really runs the state updater at render time, and presses the scan button, so this class of error can no longer reach a release.

22 days agoModels & ProvidersMIT
F

dsh-rice-mode

frisk325/dsh-rice-mode

Three-position toggle (off / this turn / always-on) for an "unlimited mode" that injects a "do not conserve tokens" instruction into the system prompt; the "this turn" mode reverts automatically on the kernel agent/status idle event.

220 days agoDev & Plugin ToolsMIT
H

claude-on-dsh

huajikano/claude-on-dsh

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

25 days agoWorkflow & Automation