Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

304 plugins found

T

oh-my-dsh-omo-fork-chs

tacrine/oh-my-dsh-omo-fork-chs

The unofficial Simplified Chinese fork of the tri-agent agent preset (Atlas orchestration plus Prometheus planning), packaged for DeepSeek Harness as a Cordis bundle; the vendored upstream content is licensed under SUL-1.0.

28 days agoWorkflow & Automation
S

DSH-Comfyui-Prompt-Generator

self-exiler/dsh-comfyui-prompt-generator

Turns rough notes or images into ready-to-paste English ComfyUI prompts with a Chinese translation and notes, in a workspace side panel. The bundled default system prompt tells the model to drop content restrictions and refusals (override it with config.systemPrompt); image input needs a vision-capable model.

23 days agoUI Enhancements
A

dsh-content-search

appthin/dsh-content-search

Searches the whole conversation — not just the loaded window — from a button in the conversation header, opens the results in the right sidebar, paints every keyword yellow in both your messages and the replies, and jumps the conversation to the hit. History search runs on the host log, so it still works when the full-text index is disabled.

212 days agoSessions & MessagesMIT
S

dsh-zh-cot-fidelity

suangxx/dsh-zh-cot-fidelity

全局系统提示词插件:中文思维链、内容保真、反八股,15 组规则全场景生效;规则文本可编辑,改完即生效

215 days agoTools & CapabilitiesMIT
L

dsh-local-trim

leonlee114514/dsh-local-trim

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

2yesterdayModels & ProvidersMIT
J

voice_for_dsh (voice-for-dsh)

junarch/voice_for_dsh

Reads each reply aloud in natural spoken language, summarizing structured content such as tables and code blocks, with an adjustable script length — from detailed narration close to the source length down to a minimal briefing. Engines: system TTS, the DeepSeek TTS API, Doubao (dialects and expressive delivery), or the local Kokoro model, which synthesizes offline in-process. It also provides three session sounds — a repeating tone while the agent works, a completion tone at the end of a turn, and a question tone when it needs your answer; built-in tones can be switched and custom audio uploaded, with files kept on the local machine.

22 days agoVision, Voice & MultimodalMIT
O

dsh-wx-archive

opencamel/dsh-wx-archive

A wx_archive tool that turns a WeChat Official Account article link into a permanent Markdown snapshot via the 2100laike archive service: images are re-hosted so they never break, snapshots survive article deletion, resubmits dedup-hit and return the latest version without spending quota, a content_kind field tells text articles from sticker (image-post) messages, and refresh forces a refetch with a PAT. Needs the third-party 2100laike service; anonymous use is limited to 8 archives per day per plugin instance and a registered PAT raises that to 100 per day.

225 days agoTools & CapabilitiesMIT
J

dsh-question-timeout-protection

julardepick/dsh-question-timeout-protection

A plugin for dsh: once ask_user_question times out, the content you entered will remain in the UI or model context.

23 days agoUI EnhancementsApache-2.0
A

dsh-backup-sync

arlenman/dsh-backup-sync

Backup, restore and machine-migration for DSH: packs skills (which live outside ~/.dsh, in ~/.agents/skills), plugin manifests, core config, memories, todos and optionally sessions into a tar.gz with a sha256 sidecar, then imports it on another machine as a three-way merge against a baseline, listing per-file differences instead of overwriting changes made there. Credentials never enter an archive (filename deny-list of 27 names plus 7 private-key suffixes plus a content gate, enforced again on the import side), every import writes a pre-restore snapshot first, and an archive can be uploaded to any WebDAV server and pulled back on the new machine. Also includes scheduled backups, a read-only viewer for individual files, and an in-panel cloud card; no npm runtime dependencies (packing uses the system tar).

2last monthDev & Plugin ToolsMIT
J

dsh-ascii-whales

jryang1997/dsh-ascii-whales

Overhead conversation background with five whale species formed from custom text or ASCII, shaded cells, frosted content cards, input-box avoidance, independent dives, spouts, ripples, wind, and cloud shadows.

215 days agoThemes & AppearanceMIT
C

dsh-file-finder

chzisnull/dsh-file-finder

File search palette for the DSH workspace: find files by name or content, open results in DSH's native right-sidebar preview, and edit text files inline with version-conflict checks.

213 days agoUI EnhancementsMIT
L

dsh-novel-reader

laoganr/dsh-novel-reader

Local TXT novel reader in the DSH right sidebar: bookshelf with file, directory and path import, chapter table of contents with jump, click-to-turn or vertical-scroll paging, reading progress restored across restarts, and font, line-spacing, background and night themes.

2last monthUI EnhancementsMIT
A

dsh-right-click-menu

al1ghtm3ter/dsh-right-click-menu

Adds a right-click menu to the DSH web UI for files and for links: a file-tree row, a file path or file mention in a chat message, or a hyperlink opens a menu that previews a file in DSH, opens it in the default application or a chosen associated one, reveals it in the file manager, copies the path, the workspace-relative path, the file name, the link address, the link text or the file contents, saves a copy elsewhere, and opens an HTTP(S) link in the sidebar browser or in the system browser, while a right-click that is not on a file or a link keeps the browser's own menu.

2last monthUI EnhancementsMIT
P

dsh-gongwen-word-check

perrylink/dsh-gongwen-word-check

Checks an official document's type and reference number against the published party and government document format standard - including the bracket form the year is written in and the numbering pattern. Reports what does not match the format; it does not judge the document's content.

28 days agoTools & CapabilitiesApache-2.0
H

dsh-recent-sessions

huangxp12/dsh-recent-sessions

Lists recent sessions across every workspace in one panel, with time grouping, two sort orders, content search, reveal-in-file-manager, and local notes that offer to insert themselves into the draft.

2last monthSessions & MessagesMIT
D

dsh-attention-health

donghangxunlang-cmd/dsh-attention-health

Content-degradation detection (thinking loops, output repetition) for DeepSeek Harness, with a continue-vs-handoff cost verdict and zero-model handoff documents.

2last monthSessions & MessagesMIT
H

dsh-conversation

huangfuren/dsh-conversation

Conversation outline panel for the DSH web surface: user questions as root nodes (index, time, tool count and text volume per turn) with the Markdown headings of assistant replies hanging beneath them, plus level slider, search scope, bookmarks, copy and export as Markdown, section jump, keyboard navigation, a right-edge density rail and per-session reading-position memory. Read-only UI: it never touches prompts, tool results or provider traffic, and writes nothing outside its own localStorage keys.

25 days agoUI EnhancementsMIT
N

insta360-ai-content-studio

nicecx/insta360-ai-content-studio

Automated daily content pipeline for Insta360 GO 3S: BLE/WiFi remote capture of aquarium footage, wireless import, ffmpeg quality evaluation with decision log, Auto editing (segment selection, TTS narration, music, subtitles), and Bilibili upload via biliup (dry-run by default).

23 months agoTools & CapabilitiesMIT
W

dsh-message-injector

wf-ping/dsh-message-injector

Presets message-injection content combos and auto-injects them into every message.

222 days agoUI EnhancementsMIT
N

dsh-session-toc

notload/dsh-session-toc

A floating right-side table of contents (TOC) for the DeepSeek Harness Web UI: one entry per user question, click to scroll to that message.

23 months agoUI EnhancementsMIT
M

dsh-backstory

meghanbao/dsh-backstory

A `/backstory` command and tool that annotate each line with the git commit that last touched it and the agent turn + prompt that wrote it, from a persistent per-line ledger (drift-proof by content hash), DSH-* commit trailers, or the live session log.

23 months agoGit & Code ReviewMIT
J

dsh-sseye

jhuanxx44/dsh-sseye

LLM debug console for DeepSeek Harness: captures the full content of every model call at the llm/stream waterfall (options, stream chunks, usage, wire protocol) and shows it in a DevTools-style docked panel, with shared-prefix context diffing, wire-JSON reconstruction, JSON export and a runtime-tunable capture policy.

2last monthDev & Plugin ToolsMIT
X

dsh-grok-geo

xuboboo/dsh-grok-geo

GEO brand audit skill bundle: AI-search visibility, recommendations, citations, competitor presence and content-gap diagnosis across 17+ AI engines (ChatGPT/Perplexity/Claude/豆包/DeepSeek/Kimi/文心一言).

23 months agoSkillsMIT
A

session-reader-plugin

artificialwhale/session-reader-plugin

Read another session's content (messages, tool calls/results, thinking) from within a DSH session

23 months agoSessions & MessagesMIT