Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

396 plugins found

D

dsh-bash-rtk

deeptrial/dsh-bash-rtk

Route eligible shell commands through rtk to compress tool output and save tokens.

18last monthTools & CapabilitiesMIT
R

dsh-fast-mode

regrevia/dsh-fast-mode

DeepSeek Harness's own fast mode: the same model on the same reasoning effort, fewer output tokens, all prompt-side. Only the output-discipline switch is on by default (late mode, active from step 4); every other switch is off and can be enabled on its own; turn on the tool-output trim switch when tool output is long. Measured on one machine, not a leaderboard: 30 task pairs with long output at the trim switch 0.756x wall clock and 21% fewer output tokens; 24 pairs on 6 real pallets/click PRs 0.805x and 23% fewer. On official SWE-bench Lite instance definitions with a self-built harness it does not show a gain (8 instances, three independent runs pooled to 72 pairs: 0.933x wall, 0.903x tokens, wall still crosses 1; single runs of the same configuration differ by 30%), and stacking switches on top of the trim switch is worse than the trim switch alone. Numbers and repro in the repo.

174 days agoUsage & BillingMIT
1

dsh-cyberegg

1015677515/dsh-cyberegg

One sidebar panel that shows the remaining credit balance and today's check-in state of every freebie platform already configured on the machine (Loomy, MiniMax Code, Trae, Qoder, Raccoon, WorkBuddy, CodeArts, WPS Lingxi, MobileClaw), read through the plugins that own each platform plus two bundled read-only readers. Query and manual check-in only: no login UI, no stored tokens, and a manual check-in is reported as successful only when the measured balance actually increased.

152 days agoUsage & BillingMIT
2

dsh-sw-cad

27painter/dsh-sw-cad

Registers two MCP servers that drive the installed AutoCAD and SolidWorks desktop apps over COM, plus two on-demand skills and a delivery check. Windows only, Python 3.11+; the pinned upstream servers install themselves on first load, and only the sides whose CAD application is registered get a row. Both servers advertise search entry tools rather than their full catalogs (2 and 3 tools), taking the schemas loaded before the first request from 83,732 to 365 tokens and from 23,411 to 474. dsh-sw-cad deliver reads what a job produced -- DXF dimension entities, units, sheet size, stated scale, PDF text layer, STEP schema and bounding box -- and exits non-zero when it does not hold up; its half-delivery profile also requires fits, material grades and surface finish to come from a bundled standards table.

155 days agoTools & CapabilitiesMIT
H

dsh-get-it-for-free

hulibuld/dsh-get-it-for-free

Connects free and check-in account channels to DeepSeek: Huawei Cloud CodeArts, Tencent CodeBuddy / WorkBuddy, Qoder, TRAE, Raccoon, LobsterAI, MiniMax, ZCode and iFlytek Loomy. Sign in to each channel in settings, claim the daily check-in where the channel offers one, sync the available model pool, and use those models as ordinary providers in the model picker, with a local usage dashboard that counts requests and tokens per account and model. Credentials stay in ~/.dsh/get-it-for-free/ on this machine; no telemetry and no requests to upstream repositories. Its optional LAN relay is off by default and listens on 0.0.0.0 when you enable it.

142 days agoModels & ProvidersMIT
B

dsh-live-token-stats

better-er/dsh-live-token-stats

Live token stats under the DSH Web composer: streamed tokens/s, output token and first-byte latency, plus per-step estimate-vs-actual reconciliation using the official BPE tokenizer, to tell a slow stream from a stalled one.

133 days agoUsage & BillingMIT
H

dsh-smart-compact

hoyyang/dsh-smart-compact

Context window auto-management for DeepSeek Harness: when the window fills up it rolls over to a fresh one with zero summarization model calls, archiving the old window verbatim for line-by-line recall; handoff anchors carry task orientation, working notes survive compaction, and a stale-notes gate warns instead of vouching for outdated notes. The trigger follows the provider budget equation (window - max_tokens) and the real routed model even after a mid-session switch. One-click composer button plus /smart-compact, three-band automatic rollover, mandatory anchor sanitization; works out of the box.

1213 days agoSessions & MessagesBSD-3-Clause
L

dsh-token-monitor

licyer/dsh-token-monitor

Header quota badge plus a usage-monitoring tab: live balance/quota remaining and reset countdown per provider, with requests, tokens (input/output/cache-read/cache-write), cache hit rate, estimated cost and average TPS tracked per session, provider, model and client, stored locally in SQLite with cross-device import/export.

122 days agoUsage & BillingMIT
Z

dsh-llm-retry-settings

zeng6125-rgb/dsh-llm-retry-settings

Settings card for the DSH LLM auto-retry engine: tune retry count, backoff and jitter live from Settings -> General, with configurable retryableCodes chips - defaults add INVALID_REQUEST so OpenAI-style HTTP 400 reasoning_text errors in thinking mode get retried automatically.

1224 days agoModels & ProvidersMIT
1

agent-body

1420079678-ctrl/agent-body

Plugin coordination layer: plugins declare their capabilities, commands route to the owning plugin without a model call, tool schemas load on demand to cut prompt tokens, run history consolidates into long-term memory while idle, and failures are classified before any retry.

112 months agoDev & Plugin ToolsMIT
D

dsh-context-compression-improved

drscrewdriver/dsh-context-compression-improved

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models. Within a turn it supports skeletonized information compression with a low original-text retrieval rate; at the tail of a turn it supports a turn-tail intent summary implemented purely by content substitution; context content stays safe, and the whole process runs inside the official JSONL compression.

112 days agoSessions & MessagesMIT
P

dsh-ui-harmonizer

physicolor/dsh-ui-harmonizer

UI harmonizer for DeepSeek Harness: normalizes unfinished or self-contradictory official UI, reconciles style conflicts between installed plugins, and unifies the visual language via official design tokens — with live-customizable chat width, markdown font size, workspace scale, UI font stack and a rounded center-column card from Settings → General; client-only dsh bundle, zero model cost, no host side, removable without residue.

1110 days agoUI EnhancementsMIT
D

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.

107 days agoVision, Voice & MultimodalMIT
J

dsh-tokenslash

jessenreinhart/dsh-tokenslash

Intelligent token optimization via Jev System One triage, dynamic tool pruning, and subagent routing.

1019 days agoUsage & Billing
L

dsh-liangxiang

liang-today/dsh-liangxiang

Burned DSH tokens become incense; spend one stick to raise or lower today's case. The case updates daily, Liangwei decides today's Liangzi, and the result is archived at day end.

1012 days agoJust for FunMIT
P

harness-ui-enhancer

physicolor/harness-ui-enhancer

Web UI polish layer for DeepSeek Harness: normalizes unfinished or self-contradictory official UI, reconciles style conflicts between installed plugins, and unifies the visual language via official design tokens; live-customizable chat width, markdown font size, workspace scale and UI font stack.

103 months agoUI EnhancementsMIT
M

dsh-plugin

morlay/dsh-plugin

css-in-js styling kit (styled / Token / Styling) for the forked conversation UI: consumes the official --dsw-* design tokens, so no CSS Modules precompile step is needed.

92 months agoUI EnhancementsMIT
G

Every-token-you-spend-comes-back-as-a-waifu.

guihui2538/every-token-you-spend-comes-back-as-a-waifu.

Turn your DSH token usage into a gacha game: feed a monster with tokens, earn coins, pull from 14 AI waifus (Kimi/GLM/Gemini/Claude and more), enhance artifacts, and build a Balatro-style battle team with daily sign-in bonuses.

83 months agoJust for FunMIT
S

dsh-oauth-mcp-client

springbrand-lab/dsh-oauth-mcp-client

OAuth 2.1 MCP client for Streamable HTTP servers: add a connection in Settings, sign in through the browser (PKCE with dynamic client registration), and have its tools registered in DSH, with tokens kept in the credential service and the connection written to the profile.

83 months agoMCP & ConnectorsMIT
L

dsh-hitchfin

luckyonetwothree/dsh-hitchfin

Bring WorkBuddy, Qoder and Trae subscription models into DeepSeek Harness with multi-account failover, per-account HTTP(S) proxies and model visibility controls. Sign-in and chat calls go through the community opencode-*-auth adapter packages (installed with the plugin at pinned versions) to each vendor's China-region service; accounts and tokens are kept in DSH's credential store, and a free-models-only filter is on by default.

75 days agoModels & ProvidersMIT
2

dsh-moli

27painter/dsh-moli

Drives a locally installed Moli headless browser from DeepSeek Harness: rendered fetch, JavaScript evaluation, Markdown, semantic trees, screenshots and PDFs. A CSS selector returns one container rather than the whole page (measured 40-80x fewer tokens on listing pages) and scroll triggers lazy loading. Installs Moli when it is missing; verified with a real engine on Windows, Linux and macOS.

72 days agoTools & CapabilitiesMIT
S

dsh-token-saver

shaw529/dsh-token-saver

DeepSeek Harness plugin that aggressively saves tokens without affecting task quality: lossless head/tail truncation of tool results (default), grep-result folding, pressure-triggered dsh-compaction-basic delegation, and an LLM-summary CompactionEngine subclass for the aggressive mode. Saves 97.6% of input tokens on an 8-scenario synthetic suite, with all reductions routed through dsh event flow so model-visible = logged stays intact.

73 months agoUsage & BillingMIT
P

dsh-widgets

physicolor/dsh-widgets

A customizable widget rail for the right side of DeepSeek Harness: 61 cards covering session stats, tokens and cache, context, background jobs, subagents, machine metrics, OpenCode Go and Command Code quota, session cost, peak pricing and the GitHub review queue. Cards install from an in-rail market into 1-4 column grids and 2x2 or 2x4 tiles, with per-instance settings, a magnification wave under the pointer and a one-click hide. Works on DSH 0.1.x and 0.2.x, web UI and desktop app.

79 days agoUI EnhancementsMIT
N

dsh-compact-suite

noirabaka/dsh-compact-suite

Takes over the compaction threshold on every mounted engine: forces headroomTokens to -1e6 so the ratio is the only term in the trigger, keeps retention below it on every write path, reroutes the compaction call to a chosen model, and adds a panel with a one-click compaction button and a per-session compaction log.

626 days agoSessions & Messages