Plugins
Browse, filter, and install DeepSeek-Harness plugins.
16296 plugins found
dsh-fail-logger
areium/dsh-fail-logger
Auto-log failed tool calls across native tools, PTC run_code, and inline invocations: dedup and count root causes into a skill so repeated mistakes fade.
Code2Skill
leechen298/code2skill
Generate Functions, MCP tools, workflow Skills, and offline test packages from user-authorized source code.
dsh-im-bridge
biboyang/dsh-im-bridge
Two-way WeChat (iLink) bridge: turn-end and approval-request push, in-chat approve/reject and message injection, persistent dedup and convergent long-reply chunking; channel layer extensible to other IMs.
kivotos
dsh-labs/kivotos
Open and drive every dsh on your tailnet from any dsh, with a complete phone layout.
DSH-Modern-UI (modern-ui)
iroha1145/dsh-modern-ui
Replacement web interface for the unmodified official DSH release: collapsible reasoning groups, a turn timeline with adjustable reading width, cards for tool calls, a model and reasoning-effort picker, an Agents view that shows subagents as a tree, optional chart and diagram widgets in answers, light and dark themes, and a phone layout. Installs from npm; uninstalling restores the official interface. An optional jev_presentation_advice tool, enabled only once you save a TypeSafe key, sends up to four recent user messages and a short outline of the planned answer to api.typesafe.ai.
dsh-better-display
adamaik/dsh-better-display
A calmer reading view for DeepSeek Harness: native process details, live reasoning, and clean final answers.
dsh-plugin-yushe (plugin)
yuna78/dsh-plugin-yushe
YuShe, a Dafeiyu (big fat fish) virtual pet for DSH: a guided visual setup hatches an AI fish girl with her own personality (15 species, 16 poses each, 200 stat points you allocate), who chats with you, answers in the workspace you bind her to, browses Bilibili on her own account and grows from what she sees, and reports back with a daily plan, diary, letters and, once you configure an image-generation API, photos; everything she posts goes through a local content gate.
dsh-eva-skins
iris-change/dsh-eva-skins
Four EVA-themed skins for DeepSeek Harness — Units 02, 00, 01 and 08. Each one restyles the sidebar, composer and window frame from the theme token layer, and ships a 20-second canvas boot sequence with a confirm step, a skip button and a replay hotkey. Switch skins from a popup on the composer chip.
dsh-thinking-language
liangzz1998/dsh-thinking-language
Injects one system-prompt section that makes the agent reason and answer in a chosen language (Simplified Chinese by default), with separate thinking and answer settings, a custom extra line, and support for standard, PTC and custom presets; the minimal preset is not affected.
dsh-workbench
chengyunlai/dsh-workbench
Open source links from DeepSeek Harness conversations at the referenced line, review Git diffs beside the chat, inspect paused variables, and turn explanations into searchable Markdown memory cards. The workbench also shows Python class relationships (beta). Go and Java navigation require language servers, and breakpoint debugging requires a debug adapter.
dsh-egm
dryw/dsh-egm
Design-review gate for DeepSeek Harness, a DSH port of Google's Elephant-Goldfish Model: a context-rich Elephant session drafts the design, then fresh, zero-context, read-only Goldfish reviewers stress-test it before implementation. Registers the `egm` plugin id; install one EGM bundle per profile.
dsh-wb400-guard
curo22/dsh-wb400-guard
Rewrites the blocked at-sign and four channel fingerprints in system messages at the fetch layer, so WorkBuddy's China gateway stops answering DSH requests with HTTP 400 code 11128; dry-run mode only observes and never modifies the request.
dsh-video-vision
destinhue/dsh-video-vision
Five tools for reading a video as raw material rather than as something to watch. video_outline maps a whole file as text and draws nothing at all: 4-60 equal windows, each with its cut count, speech share, intensity bar and tags, then the windows worth opening and the exact start/end for the call that follows -- zero image tokens. video_probe returns metadata and a reading plan without decoding frames. video_storyboard turns a window into one contact sheet plus a text index binding every cell to its timecode, cut count and frame time; cells whose text would be illegible at that scale are marked zoom, and dedupe global folds a picture that comes back after a cut. video_zoom re-renders 1-9 cells from a short window at a larger scale. video_read decodes only keyframes, OCRs each screen, and returns an outline plus \[mm:ss] text -- the path for lectures, slide decks and screen recordings, where the words are the content. It also reads a file with sound and no picture as a transcript (subtitle track, then DSH_ASR_CMD, then a transcript file you pass; long audio is cut at 45 s onto silence), composes six changed frames into one sheet when a file has no readable text at all, and can write the result out as SRT, WebVTT or text. Cuts, dissolves and one-frame flashes are found in a single ffmpeg pass; from ten minutes up a file is analysed on its keyframes only, 2.7x faster on a two-hour lecture; and a cell is never shrunk below a fifth of the source, so a 1440p sheet spends the same tokens on fewer, bigger cells. OCR is the engine Windows ships, tesseract with line boxes, or DSH_OCR_CMD. It takes a B station link (bilibili.com/video/BV..., a bare BV id, an av id or a b23.tv short link) wherever it takes a file: up to 300 seconds is read from the CDN in place with nothing written to disk, longer videos are downloaded once and cached within a 4 GB / 24 video budget, play URLs are cached for ten minutes, and a link that is not a single video says what it is. Needs ffmpeg, uses ffprobe when present, and has no other runtime dependencies. It is a wire-compatible reimplementation of SAOS-3624/dsh-video-storyboard: it registers the same video_probe / video_storyboard / video_zoom tool names, so the two cannot be enabled together.
dsh-session-header
homily707/dsh-session-header
Injects an x-session-id HTTP header carrying the harness session id onto every LLM provider request, plus whitelisted gateway fetches during tool execution.
dsh-dev-workbench
longerwu2026/dsh-dev-workbench
Workbench with an AI assistant, pause/stop controls, separate background-model settings, tasks/replies, Linky, scoped knowledge capture, local and Yunzhijia search, news reading and developer tools. Optional embeddings download a model. Yunzhijia needs its CLI/account; web chats need the desktop app.
yugoo-design (dsh)
alibaba-damo-academy/yugoo-design
Turns your AI agent application into an interactive workspace for ideation and design, with editable panels, structured knowledge and guided iteration.
dsh-ctxopt-compaction
chunsi-w/dsh-ctxopt-compaction
Bounded context compaction, session-scoped summary reuse, explicit memory controls, and diagnostic-preserving tool pruning for DeepSeek Harness. Adapted for dsh 0.2.1-rc.2, including the Web preset roster and localized plugin metadata.
dsh-isolation-gate
huanlin-labs/dsh-isolation-gate
Per-directory access gate for DSH: deny / read / full levels for names and paths, roster groups, per-session overrides and an audit log, plus seven model-facing `gate_*` tools whose widening requests must be approved by the owner in the panel. Installs with `dsh plugin --profile desktop add dsh-isolation-gate`; MIT, no network calls, state stays on disk.
dsh-media-lens
drscrewdriver/dsh-media-lens
All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can cite concrete frames, seconds and speakers — Evidence, not imagination. One failover chain per media, recorded hop-by-hop in meta.attempts (a fallback is never silent): host-registered multimodal models first, then a configured OpenAI-compatible endpoint (comma-separated multi-key rotation), then local ffmpeg frame-sampling / a local ASR CLI, degrading to metadata-only as a last resort. Absorbs modlens battle-tested rules — cooldown keyed only on auth/quota failures and softened to chain-tail (never dropped), redact-before-clip error text, magic-byte sniff that never trusts file extensions. Optional vision-bridge registers a media-lens wrapper into the host model selector so a pure-text model gains image/audio/video sight. Registering / authenticating multimodal models and true inline audio-video upload lean on two companion plugins, declared as optional peers (absence auto-degrades, never errors): dsh-thinking-levels fronts the model config / registration surface, dsh-llm-openai-completions takes over the OpenAI-compatible transport that serializes file blocks into video_url / input_audio. Privacy: media goes to remote providers by default; strictLocalOnly keeps content on-machine. Prerequisites not shipped with the package: ffmpeg/ffprobe on PATH (frame sampling / reencode / duration probe; degrades to metadata when missing) and a user-configured local ASR CLI for the audio fallback. Hosts 0.1.7 / 0.2.0 / 0.2.1 (6 rc, exact engines.dsh enum). npm: dsh-media-lens.
windowseat
zoe1nan/windowseat
Windowseat bridge for DeepSeek Harness: a local host plugin exposing a loopback HTTP/SSE endpoint so the bundled Microsoft Edge side-panel extension can read the current page, search local files and talk to DSH; the Edge extension lives in the same repo and must be loaded separately. Windows 10/11 with desktop Edge required.
dsh-chrome-bridge (plugin)
orderg-x/dsh-chrome-bridge
Controls the Chrome you are already logged into: the model clicks, types, fills in forms, reads pages, takes screenshots and downloads files in your real tabs, including inside same-origin iframes. Runs on macOS, Windows and Linux; needs Chrome 116+ and Node 18+. Works over native messaging and chrome.debugger instead of a listening port. Ships 12 browser_* tools and a cb CLI, dispatches real CDP input events, draws an on-page cursor that also appears in screenshots, and adds a toolbar panel with live status, the controlled tabs and a pause switch. browser_download saves a link, an element's target or a URL with the site's login cookies (following redirects, keeping the server's file name) to the Downloads folder or the session's working directory; cross-origin iframes are named in the snapshot but not entered. The native host and the MV3 extension travel inside this tarball: on first load the plugin copies them into place and writes the native-messaging registration itself, so there is no clone, no install.sh and no python3 - the one step left is adding the extension to Chrome: install DSH Bridge from the Chrome Web Store (https://chromewebstore.google.com/detail/bippcbbbipppmhjkjomgdnjbooecbimo, no Developer mode), or load the bundled unpacked copy at chrome://extensions (the plugin opens that page and puts the folder on the clipboard for you). Until then the tools fail loudly with those steps. On Windows the registration goes into the registry (for Chrome and Edge) and the host talks over a named pipe. A daily CI run on GitHub's macOS, Windows and Linux machines installs the plugin, loads the extension into a real Chrome and reads a page through the browser_* tools.
dsh-ai-library
instant-king/dsh-ai-library
Local library panel for DSH: indexes files and artifacts into a searchable card tree with PDF, Office and image preview, plus paper search across arXiv/OpenAlex/Crossref and others, web-page archiving to markdown snapshots, a plugin-market tab, and one-click switching for resources found in installed plugins (personas, meme packs, whale widget assets). Ships 18 tools and 22 host routes.
dsh-reply-forge-v3
kinggod899/dsh-reply-forge-v3
Edits assistant replies and thinking chains in DSH sessions so the model sees the edited text, live via message projection or on disk.
dsh-structured
feigo313/dsh-structured
Persona mode + structured output for DSH: identity header, three cards and signature rendered by the plugin while the model only submits a persona JSON envelope; per-session structured toggle, default-on persona.