Best · Curated
Best DSH Model & LLM Switching Plugins
Switch DeepSeek Harness to any OpenAI-compatible endpoint, with fallbacks and provider presets.
Editor's pick
Editor's pick
Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.
Ranking
Development & Runtime plugin ranking
019817,548 downloads/mo02728,171 downloads/mo03556,613 downloads/mo04644,493 downloads/mo05624,385 downloads/mo06644,364 downloads/mo07744,214 downloads/mo08694,068 downloads/mo09723,982 downloads/mo10743,726 downloads/mo11593,587 downloads/mo12663,585 downloads/mo13723,525 downloads/mo14423,397 downloads/mo15743,388 downloads/mo16643,380 downloads/mo17773,357 downloads/mo18692,977 downloads/mo19712,879 downloads/mo20692,817 downloads/mo21692,782 downloads/mo22642,776 downloads/mo23562,760 downloads/mo24672,732 downloads/mo25722,705 downloads/mo26672,562 downloads/mo27642,461 downloads/mo28642,325 downloads/mo29642,198 downloads/mo30642,164 downloads/mo31662,155 downloads/mo32702,086 downloads/mo33692,002 downloads/mo34691,997 downloads/mo35671,886 downloads/mo36671,864 downloads/mo37671,842 downloads/mo38741,827 downloads/mo39621,748 downloads/mo40521,534 downloads/mo41671,486 downloads/mo42671,451 downloads/mo43611,449 downloads/mo44621,423 downloads/mo45671,362 downloads/mo46691,342 downloads/mo47691,312 downloads/mo48621,307 downloads/mo49621,284 downloads/mo50711,272 downloads/mo51671,249 downloads/mo52721,228 downloads/mo53661,219 downloads/mo54741,214 downloads/mo55691,209 downloads/mo56641,207 downloads/mo57641,167 downloads/mo58641,117 downloads/mo59391,109 downloads/mo60621,072 downloads/mo61671,064 downloads/mo62671,049 downloads/mo63691,043 downloads/mo64621,040 downloads/mo65621,033 downloads/mo66671,001 downloads/mo6766930 downloads/mo6864926 downloads/mo6956899 downloads/mo7064882 downloads/mo7166876 downloads/mo7259870 downloads/mo7364868 downloads/mo7461856 downloads/mo7563855 downloads/mo7666835 downloads/mo7766804 downloads/mo7864793 downloads/mo7961780 downloads/mo8061779 downloads/mo8171738 downloads/mo8261737 downloads/mo8366679 downloads/mo8464676 downloads/mo8566670 downloads/mo8661657 downloads/mo8759499 downloads/mo8861499 downloads/mo8959493 downloads/mo9068484 downloads/mo9159423 downloads/mo9268379 downloads/mo9369357 downloads/mo9464340 downloads/mo9563330 downloads/mo9668327 downloads/mo9764317 downloads/mo9861229 downloads/mo9956192 downloads/mo10061112 downloads/mo
Anionex/dsh-vision-toolkit
Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.
accpowered/dsh-auto-review
LLM approval answerer for sandbox escalations beyond workspace-write: a deterministic regex filter first, then a clean-context reviewer model; humans are asked only when it is unsure. Requires the bundled core patches.
f-e-n-g-0531/dsh-code-report
Compare Git/SVN versions across repositories and export Chinese Markdown release reports with optional approved model analysis.
IamNewHands/dsh-approval-gate
Maintained fork of dsh-approval-gate. A neutral operation whose confirmation count has reached the threshold auto-approves when the judge is unavailable, instead of prompting a human again; approver-facing explanations are generated in Chinese from the real sandbox mode, command and paths. Also carries deterministic hard-deny for credential exfiltration and system-path destruction, judge-input redaction, a judge model candidate chain, fingerprint-scoped allow rules, and an approval view with unified diff and one-click revert.
AmethystLuna/dsh-model-everything
Turns what a design, plan or document claims into a model and decides it: UML diagrams rendered, read and reviewed; state machines, protocols and data models checked as models; migrations tested for coverage and rollback symmetry; concurrency claims mined and routed to the checker that can decide them; dependency graphs audited; reports diffed.
zqh260619/dsh-dupguard
Stops a streaming model call when the same string repeats ten times in a row (threshold configurable), keeps the partial answer as a normal assistant message, and shows a stop notice with the workspace, session name and the repeated string. Repeat counts can vary by unit length through a piecewise table or a JavaScript module, and code regions (fenced, inline, indented) use a relaxed threshold.
gehennawu/dsh-service
Self-hosted DSH Web operations panel for safe restart and upgrade, health diagnostics, model-usage statistics and provider quota lookup, backup and session management, task notifications, skill controls, subagent model routing, and Linux permission maintenance.
MoonlitDropOfBlood/dsh-deveco
HarmonyOS development suite for DSH: a right-sidebar HiLog inspector (live stream with level/logger/text filters) and an ArkUI Inspector (screenshot pick, collapsible component tree, node properties with search, box model), two tree sources — the DevEco debug channel (declared padding/margin/border and custom component names) and the uitest accessibility tree — an .ets viewer with ArkTS syntax highlighting, DevEco Studio/CLT toolchain and device management, plus the harmony_ui_tree agent tool. 21 remote methods, 82 unit tests.
drliuhuan/dsh-plugin-pwsh7
Replaces the Windows pwsh executor row so the model-facing pwsh tool runs PowerShell 7, with a shell_router tool for status, diagnosis, and per-user portable installation.
x5427876/dsh-opencode-free
Free OpenCode Zen models in DeepSeek Harness, anonymous by default with an optional Zen key. The catalogue is read from Zen's official model list at runtime, and anonymous requests are adapted to the free tier's request checks, documented with dated measurements.
a1249070611/dsh-hoi4-modding
DeepSeek Harness skill bundle for Hearts of Iron IV 1.19.3 modding: registers 15 skills and mounts 20 local MCP tools (a Python stdio server) to scaffold, statically verify, install and debug mods - focus trees, events, decisions, ideas, characters, technologies, MIO, special projects, scripted GUI and topbar buttons, localisation, DDS icons, 18-slot tank designer layouts, 3D tank models, CJK font auditing and error.log triage - plus a 23-workshop-mod technique survey and a multi-agent playbook. Requires DSH >=0.2.0 <0.3.0 and Python 3.9+ on PATH (standard library only, no third-party packages); no game assets are shipped.
Dclef/dsh-cursor-dev
Runs the local Cursor CLI as a child coding agent from DSH - a `cursor_code` tool plus the native one-shot `cursor_subagent` tool, one mirrored DSH sub-session per run, per-task model choice, resumable conversations, a step timeline with real file diffs, and a usage, model and session panel.
PerryLink/dsh-fast
Read-only performance diagnostics for DeepSeek Harness: session load/restore timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via /fast, persisted as reconstructable session events with async sampling off the model path.
Bingtang1019/dsh-ppt-fusion
Build PowerPoint decks from a brief: plan and storyboard gates, per-page authoring through pptwise and ppt-master, a design-profile pass, page-image snapshots with a render audit, and a tool that hands those pages to an image-capable model for review.
SeverusZh/dsh-plugin-subagent-director
Subagent Director: per-subagent LLM provider/model selection with role templates for DeepSeek Harness (dsh plugin)
regrevia/dsh-lifeguard
Turns real DSH crash logs into a short hard-constraint list: static preflight before a plugin installs, conflict check afterwards, controlled self-heal when the harness will not start — plus handing a huge session over to a fresh one, the brief written by a model that reads the original transcript.
guo6x/dsh-pilot
Zero-dependency browser control: drive a real headless Edge/Chrome over CDP with 8 `pilot_*` tools (navigate/click/type/keys/eval/screenshot) plus a live draggable cockpit panel in the Web GUI - text-first snapshots for text-only models, no Playwright, no API key.
MoonlitDropOfBlood/dsh-agent-approval
An independent approval subagent judges every sandbox escalation, with a configurable model and an audit log.
YunaAloft/dsh-rtk-workbench
Brings the rtk token-saving setup from Claude Code to DeepSeek Harness: commands rtk can rewrite are rewritten, and builds, tests and logs it cannot reach are compressed; git, cargo, npm and pytest are covered. Compressed output tells the model what was elided and how to recover it; when the sandbox cannot reach the rtk store the original is saved and its path given. Savings show without a command: a pill below the composer, with `/rtk stats` for detail. When a rewrite is unreliable the original command runs as usual: if rtk cannot run, or the returned command would drop arguments, nothing breaks. The rtk binary ships with the package, so mainstream platforms need no separate rtk install, unlike most other rtk plugins.
LLYlab/DSHEssentialTools
A permanent DSH plugin that bundles a developer workbench, an in-session conversation tree, and a plugin manager: build and run an LVAL project, browse its code, and keep per-program version snapshots with rollback; edit, retry, or branch any message in place, with message micro-versions; a feature manager plus a global-plugin library whose entries each carry an enable tier; cross-dialogue memory, one-shot temporary chats, and model collaboration; five network-permission tiers, mixed-model routing, a security audit, and browser control through a companion extension.
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).
KannaKuron/dsh-agent-lang
Three independent language channels for model output — tool-call descriptions (every tool-call card title, including run_code in PTC-style presets), thinking, and replies — each set to follow the web GUI language, force a specific language, or turn off (default: only descriptions, following the GUI). One global runtime-context prompt directive on the host; the client half reports the GUI language; a Settings plugin card switches the modes.
Gaudi-XIX/dsh-agy-cli
Windows-only model provider for Google Antigravity CLI. It reads the Antigravity token from the Windows Credential Manager and sends it only to the Google Cloud Code endpoints, while DSH owns the tool policy, approvals, and sandbox. Lean prompts with adaptive tool projection (base exec/file tools plus on-demand mounting via dsh_discover_tools), folding of long historical tool output, and pre-send sanitizing; streams the tail without rollback and tracks the real quota windows.
sleetdrop/dsh-plugin-topology
Dependency graph inspector for DeepSeek Harness: snapshots the live Cordis plugin/service topology into a zoomable browser panel with graph-theory metrics, plus a graph.render tool for the model.
HaoyueQin/dsh-usage-statistics-panel
Usage statistics settings panel: 26-week activity heatmap, daily token trend with a cache hit-rate curve, per-model donut and breakdown, time-range filters, summary cards, one-time historical backfill and lossless rebuild.
zhiwuli0228/dsh-env-manager
File-based environment registry for DSH: manage environments, services, deployments and operation-to-Skill bindings through a panel and model-facing tools.
benrong2048-boop/dsh-prompt-polish
Turns a one-line DSH draft into a complete task brief (role / goal / constraints / output format). The engine is a byte-verified port of linshenkx/prompt-optimizer (three modes, 10 templates identical to upstream); history is consent-gated with version chains and structural comparison; every run reports its token usage. Nothing is written back or sent without a click.
tangyixiao/dsh-provider-doctor
Read-only diagnosis for a model provider that stopped working. Walks the connection chain one link at a time — host runtime and profile identity, the plugin row, whether the provider route is registered, whether it is configurable, the credential metadata the provider itself reports, the model catalogue, the provider's own diagnostic and the last recorded request — and labels each link observed, inferred or unavailable rather than guessing. Diagnoses the `workbuddy`, `workbuddy-ai` and `zcode-cli` routes from their plugins' public diagnostic commands, and adds a sidebar panel plus a copyable redacted report. The offline pass sends no model request, starts no process and reads no credential file; the connection check is a separate opt-in the panel describes before running it.
znlgis/dsh-video-studio-skill
Registers the video-studio skill in the DSH skill catalog. It builds a Chinese-narrated video from a script: edge-tts synthesizes the narration, the timeline is derived from each line's measured audio duration rather than estimated from text length, Pillow renders every frame deterministically and pipes the raw frames to ffmpeg as rawvideo, burned-in subtitles and SRT/ASS export come from that same timeline, physical-model sound effects and a generated score are mixed sample by sample with numpy, and QA runs in four layers: container, signal, temporal and page level (the page layer only when the browser engine is used). An optional Playwright-driven browser engine renders the whole film as Canvas2D instead, sending PNG frames through image2pipe. Needs network access for the narration, ffmpeg on PATH and Python with numpy, Pillow and edge-tts; the browser engine also needs Playwright with a local Edge/Chromium.
minutiae3/dsh-thinking-zh
Registers system-prompt sections that make the model reason in Simplified or Traditional Chinese, with strict/prefer modes and an optional reply-language policy. Adds a /thinking-zh command for per-session switching. Zero runtime dependencies.
chaos-miku/dsh-error-atlas
Records DeepSeek Harness runtime errors and coding retrospectives as an interactive GPU graph, and feeds the recorded lessons back into the model's context.
xyrrrrr-r/dsh-eval-control
Host-side DSH evaluation control plugin: injects one evaluation trial's variables, budget limits, session root and fork lineage into the agent process, routes its model calls through a host broker under a gateway lease, and writes a schema-versioned bundle descriptor for evidence attribution.
wweir/dsh-advisor
Automatic second-opinion review: a restricted child session re-reads the agent's recent work with read-only tools and delivers at most one evidence-backed note, or stays silent. Requires a model route in the config; the plugin stays disabled until one is set.
Octo-o-o-o/dsh-plugin-deploy
Ship a project to Cloudflare and publish your plugin to npm — the first deploy needs no cloud account, and credentials never reach the model.
john-walks-slow/dsh-set-model
Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.
tuogusa/dsh-skill-manager
Browse, search, delete, undo-delete, and update user skills from the Web settings panel; checks GitHub/Gitee Releases for newer skill versions.
a961282799-crypto/dsh-region-edit
In the DSH desktop file preview, click an HTML element (with its source line and column) or lasso part of an image for the vision model to identify, then send your change request to the current session; local HTML edits keep a history with before/after previews, line diffs and rollback.
jasen215/dsh-continual-harness
Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.
ForceMind/dsh-atelier
A DeepSeek Harness workbench with model metrics, cost estimates, prompt presets, optional auditing, and context-aware reply suggestions; automatic suggestions default on and may incur API fees.
gongfpp/dsh-cost-voice
Dabaifan Arrival Voice Announcements speaks the estimated spend per turn with the bundled Dabaifan voice by default; Alipay is optional. Amounts come from dsh-cost-meter or model-price estimates, not payment records. No runtime TTS service. Code is MIT; the bundled Alipay clips come from Reathin/XVoice (no licence), the Dabaifan voice is a MiMo clone and the icon is a fan-made meme, all for personal, non-commercial use with this plugin only.
wjvalue/dsh-answer-me-with-html
Answers a hard question with a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled dependency-free `am` CLI builds the layout, CSS and diagram coordinates. Vendors the upstream answer-me-with-html skill verbatim as a skill-only DSH bundle with no Host code.
Endless-zby/dsh-jenkins-plugin
Jenkins CI integration with a live build-progress panel in the right sidebar, a multi-instance settings page, five model-facing tools (list jobs, build status, console log, workspace, trigger build), and a failure wake that hands a failed followed build to the conversation that followed it.
fangqian616/dsh-say
Speaks your agent's reports in a voice you choose, compressing long reports before speaking. Character voices need no training - a 3-10 second reference clip clones one, and community-trained models work too - and no 6.4 GB GPT-SoVITS install: the plugin installs its own runtime and voice. An existing GPT-SoVITS can be used instead, and it is the same voice model.
bushizhanghan/dsh-context-budget
Audit how each turn's context budget is spent. Breaks down what a turn pays for AGENTS.md, the skill catalog, tool schemas and runtime context; flags repeated injection of unchanged content as pure waste; ranks skill-catalog bloat (with 60+ skills installed, how many tokens of descriptions does the model read every turn) and tool-schema inflation per plugin. Deterministic — no LLM, so a wrong answer is a rule bug with a name. Four tools including a cross-session sweep.
viogus/dsh-rtk
Routes eligible bash commands through rtk (Rust Token Killer) so tool output is compressed before it reaches the model, by asking the installed rtk to rewrite each command and adopting what it prints; when rtk is absent the executor behaves exactly like the stock one.
songrui111/dsh-agent-bench
Runs a fixed set of agent benchmark cases in isolated sandboxes, scores each case with deterministic assertions, and diffs two runs to show which cases regressed after a model, prompt or DSH upgrade.
khglobal/dsh-nocco
Describe a web system in chat and get a working one: admin panels, mobile apps, games. See it live beside the conversation, click any element to change it, start from your Excel data, and undo any step. Four design styles; sign-in and database built in.
taoziliyouchong/dsh-evolve-preset
Evolution mode in one package: a thinking mode that aligns on your goal and boundaries each turn plus the task tree, profile injection and panel, alignment-bar styling, self-check tools and plan-mode entry — install one package and you have the whole set. It helps the model understand requests more accurately, get noticeably better results at the same cost, and build a long-term profile of your preferences. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
ajia1206/dsh-restart
Restarts the running DSH process from a model tool or a bottom-right GUI control, with launchd KeepAlive detection, a detached-supervisor fallback that aborts the exit when its handshake fails, a macOS desktop restart path, and JSONL restart records correlated by arm id, pid and profile so a restart stays distinguishable from unrelated log activity.
caizhihaoczh/dsh-profile-multica
Bridges Multica to DeepSeek Harness through a versioned JSONL process protocol.
Henta111/dsh-more-models-thinking-level
Per-model reasoning effort (off/minimal/low/medium/high/xhigh) for GPT, Codex, Gemini and OpenAI-compatible models. Installs a helper, not a runtime adapter: run enable-capabilities.ps1 once per profile (Windows) and restart — it declares the levels in ~/.dsh/settings.yaml, with a disable script and a backup to revert.
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.
x402/dsh-fail-fast
Fail-fast tool batches for DeepSeek Harness: inside a step, concurrency-safe calls still overlap, but after the first failed call every remaining unstarted call is denied before dispatch and returned to the model as a synthesized `is_error` "not executed" result.
labmimors/dsh-mcp-lens
Progressive-disclosure MCP gateway that searches large remote catalogs through `mcp_search`, then invokes exact schemas through `mcp_call` with lazy connections and bounded caches.
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.
daimingxing/dsh-reload
Three things for DSH plugin development: reload the plugins whose files changed, restart the client when a reload cannot apply a change, and let the model trigger a reload itself. Reload uses DSH's own path, so untouched plugins keep running. Restart starts outside the client, so it completes even when the client is what gets replaced, and refuses while a session or job runs. Lightweight: no parameters, no added context, buttons off by default.
Leonlee114514/dsh-better-debug
Appends one short user message before the next step when the model is circling: the same absolute path written three times with no measurement landing in between, the same error episode (tool, target and normalised fingerprint) returning twice, or a write followed by two steps with no measurement — the last one only arms, and the message lands before the next write rather than interrupting reading. A measurement has two states: intent is judged from the tool arguments at call time, and the write streak is cleared only when the result comes back, only for that command directory. A failed test still counts, because it yields the line that is wrong. Hard measurements are `lsp_diagnostics`, `verify`, `run_tests` and `run_test`; `ops_bash`, `bash`, `shell` and `pwsh` count only when the command matches a measurement pattern, so `ls` no longer launders a blind edit streak. Signals fire once per episode, re-arm after a real measurement, and are capped per turn; a successful `present` sleeps the gate until the next write, and subagent sessions are skipped. Generated paths (build output, lock files, logs) are excluded. Error targets are read out of real `file:///` ESM stacks, so two different files never collapse into one episode, and `cd <dir> && cmd` counts as a measurement of that directory rather than its parent. Ships the `stuck-gate` skill at bundled rank 600 (a user-level copy at 400 overrides its wording) plus a read-only observation panel at `/better-debug` reporting firings, sessions covered, the first action after each message across six classes, and how many measurement loops actually closed. The log defaults to `$DSH_HOME/logs/better-debug.log` and is created on first write, so the panel has data right after install. Optional host services are subscribed dynamically, so a host without them still loads the gate. It does not estimate tokens saved, and it does not claim the message caused the change. The panel banner counts only the failures after the most recent load (`log.current`), so one old mount failure no longer reads as "currently disabled". Test suites wait for log conditions instead of fixed delays (test-only change in 0.2.5).
better-er/dsh-write-create-only
Host-side guard that lets the write tool only create new files: when the target already exists it denies the call before execution and tells the model to use edit instead, applied to all sessions.
Wang-Shuanglin/dsh-cosplay-studio
Local ComfyUI cosplay photo sets for Windows with an NVIDIA GPU (8 GB+ VRAM): deploys the ComfyUI Windows portable build and Z-Image-Turbo (8-10 GB of models) with a self-test, then turns a character name, a reference image, or a hot-character pick into a live-action cosplay photo set with base-image and shot-script approval gates.
oihai/dsh-harness-trace
Records every session as one readable Markdown timeline inside the session workspace - the full request sent to the model (system prompt and plugin injections included), user input, replies, reasoning, tool calls and results, file reads and writes, web searches, skill loads, command runs and token usage - with a review page, a per-session tab and configurable capture scope.
ysiguu/dsh-novelai
NovelAI image generation for DSH: `nai_image` (style presets, artist strings, per-model weight rewriting, token budget warnings, results rendered inline), `nai_status`, and `nai_prompt` (build / check / guide), plus a studio page with live draft previews, a standalone studio server, and a prompt guide distilled from four tutorials. Bring your own `pst-` token.
FeatherHunter/dsh-chinese-skill-patch
Type /私 and complete 私家大厨 — Chinese skill names, zero renaming. Patches DSH skill discovery, the / gesture and the skill tool so any Unicode SKILL.md name (私家大厨, 卡路里, 作息管家…) works: slash completion, direct /私家大厨 invocation, model skill({name}) loading. Zero config; runtime changes revert on uninstall, but the regex patch written into three DSH packages on disk stays until the next DSH upgrade replaces those files.
maxmilian/dsh-sentry
Read-only Sentry tools: project listing, issue search at organization or project scope, single issue detail, and the latest or a specific event with a trimmed stacktrace. Local variables, request headers and bodies, query strings, packages and secret-looking tags are removed before the event reaches the model, and oversized events degrade through source context, breadcrumbs and frames rather than failing.
fu827707013/dsh-model-health-probe
Manual model probe for DeepSeek Harness: a session-view tab where you pick provider, API type, model and route, then send one real raw HTTP request over openai-completions, openai-responses or anthropic-messages — streaming or not — and read latency, TTFT, HTTP status, token usage and a three-layer diagnosis chain (API request / model response / strict check) on one screen, with errors in plain language.
h2298511604-ops/dsh-anatomy
Live architecture map of DeepSeek Harness: renders plugins, services, tools, sessions, models and MCP as a five-layer diagram of 14 component domains, and animates the real tool/model/session call flow as moving dots along the connecting curves.
huhaodong/dsh-auto-driving
Model failover and turn keep-alive for DeepSeek Harness: a request that fails with a model error before any visible output falls through the models of the configured provider groups (then the next provider) until one streams; transient failures retry with backoff under a liveness watchdog, a dead turn self-resumes with templated 「继续」 wake-ups, and an optional full-auto mode auto-answers permission, question and plan approvals with every decision appended to an AUTO-MODE.md audit log.
kissfirembx/dsh-skill-map
Sorts every loaded skill into one or more user-owned workspaces in a right-sidebar tab: each workspace is its own category list plus where every skill sits, categories are created, renamed, reordered and deleted in place, and skills are dragged or picked between them. A first run can let the profile model build the first classification, or place skills into categories the user built first; clicking a row copies its /skill-name and hovering unfolds the description the skill ships.
fu827707013/dsh-concurrency-guard
Concurrency guard and monitor for DeepSeek Harness: FIFO queue when concurrent model requests reach the limit, per-day persisted stats with error-kind classification, and interruption detection for abandoned streams.
Ndsanes/dsh-rules
Discovers rule files from every convention OMP supports and injects them into the system prompt as an always-apply layer plus a rulebook index, then enforces them with time-traveling stream rules that abort violating output mid-turn, deny a matching tool call, fold a reminder into that call's result, or ask a judge model about the finished reply. The same tool lets the model write new rules, and an audit panel on the Plugins page says why each rule is in force.
SiriusWJ/dsh-updater-npm
DSH updater + official docs sync in Settings: one-click npm update of @deepseek-ai/dsh with live progress (npm output stream, elapsed timer, monotonic bar), multi-copy protection that only touches the running instance, source-tree mode via git pull, one-click PowerShell 7 install on Windows, incremental sync of the official docs/ with progress, and the dsh_docs_search / dsh_docs_read model tools.
lolitakawayi/dsh-harness-autostart
Adds one row to Settings → General with a switch that writes or removes a Windows logon startup entry for the DeepSeek Harness desktop app, and registers a dsh_autostart tool exposing the same status, enable and disable operations. Defaults to a single HKCU Run value, no admin rights; the startup-folder launcher mode adds an optional delay and launch arguments.
zhangzhenwen1/dsh-task-effort
Auto-adjust model reasoning effort per task (off/low/high/max): task classification, \[effort=...] markers, in-turn error escalation, DeepSeek peak-pricing-period capping with countdown notices, and manual-selection priority.
wpeng77/dsh-llm-trace
Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provider calls and attributes each capture to the session that caused it through the llm/stream waterfall. The request pane renders the body as a collapsible tree with per-node sizes — one measured request was 98.6% a single 973-entry array — and the response pane reassembles the OpenAI-style SSE chunk stream into reasoning, content, tool calls and usage. Shown in a Conversation View tab and a loopback viewer page.
leotpp/dsh-subagent-toolkit
Adds a Settings page to pin one OpenAI-compatible subagent model (or follow the main model), writes the official subagent-model-selection allowlist, reminds the parent to pass that route, and optionally runs one-shot tasks through an isolated Pi CLI provider.
yoshino-xiao7/dsh-grok-provider
DeepSeek Harness 的社区 Grok Build Provider:官方 CLI 浏览器 OAuth、动态模型、流式工具调用与额度面板。Community Grok Build provider with official CLI OAuth, dynamic models, streaming tools, and a quota dashboard.
loeanxi/dsh-cursor-acp
Hands standalone jobs to the Cursor CLI signed in on the same machine, with CLI readiness and proxy diagnostics, child-model settings, and a read-only connectivity test.
Phoeky/dsh-scnet-connect
SCNet models for DSH. Free SCNet-Max, no client login needed; tokenizer, template and deterministic-output fingerprints match DeepSeek-V4.1-Flash-1017 (README). It reads the SCNet desktop client's stored login when one exists, and otherwise logs in with a phone SMS code from the settings page.
Lostforest7/dsh-apirevise
API regression and acceptance workbench: snapshot the responses of the endpoints you register before the agent edits the backend, rerun them all after the edit, and review a structured field-level diff (status codes, added and removed fields, numeric old → new values with the delta) beside the captured source diff, accepting each endpoint one by one before exporting a Markdown or single-file HTML report.
izz-BLUE/dsh-devtools
Metadata-first runtime profiler for DSH agents: turn/step traces, model and tool wall-time timelines, provider usage, retries, errors, and live or historical sessions.
LFY-bot/dsh-api-probe
Diagnoses third-party LLM API endpoints from the sidebar: a four-layer check (DNS/TCP/TLS, key and model, a real streaming conversation, then timed repeat runs) reporting time-to-first-token, output speed and success rate, with every failure attributed to the step it stalled at and the byte count that actually left the machine. 37 provider presets, no model names hardcoded.
zoahdev/dsh-plugin-doctor
Health checks for DSH plugins: manifest/patch/entry/build/pack/install verification, model-callable plugin_check, profile host-shadowing + BOM detection, environment diagnostics, and poison preflight.
Leonlee114514/dsh-turn-cleanup
Blocks the end of a turn while temporary files from that turn are still lying around: it registers a listener on the serial agent/turn-stopping hook and, if anything is left, hands the model the file list plus two ways out — delete them, or justify each one and move it somewhere deliberate. Candidates come from two narrow temp-file sources, plus a backup-retention channel that is on by default and flags excess .bak copies of files touched this turn. The first is the .agent-tmp/ convention directory under the session cwd: whatever is left in it is reported outright, because that directory exists only for throwaway files. The second is the paths this turn actually wrote, captured through the fs/write-intent, fs/edit-intent and fs/delete-intent hooks; those are reported only when they sit under that cwd (compared after realpath normalisation), fall outside .git, node_modules, out, dist, build, target, vendor, .venv and the Python bytecode cache directory, match a temp-file pattern that requires a separator after the prefix so checkout.js and benchmark.ts are not taken for scratch files, and the file is still present — which keeps junk already sitting in the workspace from being resurrected as a complaint about this turn. One gate per turn, subagent sessions skipped, nothing deleted unless the backup mode is explicitly set to prune, and the injected wording follows the host locale instead of assuming a Chinese one.
gwsbhqt/dsh-insight
Read-only insight panel for one profile: five views over the same data — config layers, plugin tree, services, tool names and models — each entry showing which layer inserted or disabled it and whether it is running.
zampie/request-frame-preview
Session-header button that previews and downloads the exact request frame DeepSeek Harness sends to the model: the full system prompt, the declared tools array, and the wire message array (system/user/assistant/tool-result) rebuilt from the session log via the same folds the agent loop reads.
eurekame2000/dsh-vision-direct
Self-contained vision for text-only DSH models: registers its own vision_read_image tool (verbatim OCR, reading-order layout, semantics, uncertainty), turns pasted images into local file paths through a capture-phase paste channel with rolling storage, and optionally exposes a loopback OpenAI/Anthropic-compatible endpoint. Talks to your own upstream directly, with no external vision CLI and no runtime dependency. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
HakureiMonika/dsh-better-tips
Recovers socket cause chains, key HTTP response headers, and size-limited error bodies from failed DSH model requests, shows them next to the native error, and adds bounded extra retries for model and compaction requests.
railgun20001/dsh-error-digest
Collects the failures recorded in DSH session logs — tool failures, turn failures and model retries — folds them into one table merged across sessions and sorted by frequency, showing category, source, error code, count, last-seen time and a summary per row. Each row can start a new session draft pre-filled for root-cause analysis or for prevention (sending still needs your confirmation), and ignoring a row only hides it in the panel without deleting logs.
shangdi178/dsh-versions
Version manager for the dsh host in a settings section of its own: shows the installed version against npm dist-tags, checks for updates, and installs, upgrades, downgrades or reinstalls any published version with a pre-upgrade local snapshot, failure rollback, snapshot-based rollback and an upgrade history. Before a cross-minor install it compares the @deepseek-ai/dsh-settings exports of the target release with the named imports of installed plugins to flag those that would stop loading, and it can apply or remove reversible compat shims that port removed legacy APIs back into framework files. Upgrade, restore and restart engines are Windows-only; version listing and checks work on every platform.
kelvin0304ykx-coder/dsh-task-readiness
Checks whether the current session can actually run a task before starting it: tool admission for the current step, model route, workspace write boundary, document engine and MCP visibility, reported per capability with evidence, plus an opt-in minimal probe and a recheck after an approved fix.
llmpolska/oh-my-dsh
Tiered model routing for DeepSeek Harness: think/build model tiers, vision delegation (the vision model only describes images; the working model acts), image generation, and a high-impact guard.
stallenlu/dsh-steward
Read-only diagnostics for a DSH install — boot-crash logs and the cause named in them, config drift against a recorded fingerprint, backup freshness, workspace growth, plugin updates, host-version compatibility, duplicate client ids, and model availability — plus an action layer that always shows a plan first and needs a single-use fingerprint and explicit confirmation before anything is written. A checkup also runs 45 seconds after every host start; when the 3-hour probe cache is stale it sends a one-line test prompt to the default model and a few models of each configured provider (model.probeOnReport can switch this off). Registers the agent tools dsh_steward_report and dsh_steward_act (clean caches via dsh-disk-cleaner, backup via dsh-config-manager, disable or enable a bundle, set the default model; execute takes the plan's hash plus confirm: true) and a system-prompt section telling the agent to run the report first when something crashed.
sequoiayunus-hue/dsh-subagent-model-config
Settings-UI editor that assigns per-teammate model and reasoning-effort rules for DSH native agent teams, resolved at spawn time by wrapping SubagentRuntime.startContinuable. No official files are modified.
zgrajdnhj7806-svg/dsh-deepseek-web
Calls your own chat.deepseek.com account as a second model from DSH: ask a question, analyze a file's line range, and check login state, plus a runtime skill and a settings-page login panel.
tangzheng202202/dsh-voice-live
Real-time duplex voice over Volcengine streaming ASR/TTS: agent reply narration, barge-in, wake word, live captions, 30 Chinese voices and a reply-first acknowledgment; builds in the DSH monorepo.
mexiaosqwq/want-a-init
Model-driven /init command: the agent analyzes the current repo and generates/updates a high-signal AGENTS.md, with a persistent system-prompt reminder to keep it maintained.
ayahunter/dsh-plugin-clinic
Read-only health clinic for the installed DSH plugin set: loader health, dependency integrity, version compatibility, install-script risk, duplicates and patch integrity, delivered as a model tool, a Settings dashboard and JSON reports.
ethanrise/dsh-model-deploy
Inspects ONNX models (inputs/outputs, shapes, opset, operators, size) and benchmarks them with ONNX Runtime on the local machine or on a remote target over SSH, reporting average/P50/P95/P99 latency, FPS and the execution provider actually used, with PASS/FAIL gates for FPS, P95 latency and model size. Requires Python 3.10+ with numpy, onnx, onnxruntime, and psutil installed (pip install numpy onnx onnxruntime psutil); remote targets need python3, numpy, and onnxruntime.
TNTD26/dsh-ide
An IDE inside DeepSeek Harness with a file tree, multi-tab editor, AI assistant with model picker and API-key setup, Git panel, PTY terminal, and Python/TypeScript LSP.
chenxiaojie1009/dsh-console
Serial and SSH device console: the panel model turns a plain requirement into commands, asks before running them, and shows Chinese annotations plus output explanations.
Lumos-789/guster
Audits and evolves agent context at four scopes: a single repository, a group of related repos, a knowledge hub, or the whole machine. Discovers projects, instruction files, skills, tools, knowledge, state, evidence and credential references; reports drift, duplicate facts, broken pointers, budget overruns, unindexed knowledge, stale state and unregistered credentials; scores each scope on its own dimensions; and turns findings into reviewable migration plans that back up every file before moving it. The format contract is a versioned spec (CTX rules, markdownlint-style IDs) following open conventions — the AGENTS.md open format, llms.txt-shaped indexes, YAML front-matter note headers — now backed by published JSON Schema contracts (draft 2020-12) for the hub manifest and the plan JSON, plus an editor modeline that validates hub.yaml with zero configuration. The hub is declarative (schema 2, zones with light profiles, sections may live outside the hub root), a one-pass check command runs scan, doctor and score, and state writes are atomic and lock-protected; scoring stays honest about missing evidence — a waiver greens the gate, never the score. Ships a stdlib-only Python CLI plus two skills; credentials are referenced by path and never printed. Requires Python 3.9+ (stdlib only) and DSH 0.2.1-rc.2 or newer, below 0.3.0.
View all Development & Runtime plugins Development & Runtime,Back to leaderboard dshplugins.cc。