Plugins
Parcourez, filtrez et installez des plugins DeepSeek-Harness.
1415 plugins trouvés
albis-aipassport-homework
albisjee25/albis-aipassport-homework
Homework helper for the AI Passport device: turns homework screenshots into a checklist with per-task countdown timers and push-to-talk, plus a parent dashboard. It runs its own HTTP server on 0.0.0.0:8787 by default so the device on the same Wi-Fi can reach it: the parent dashboard only accepts connections from this computer, and a device needs a token issued after you approve its pairing code.
dsh-model-probe
vhow123/dsh-model-probe
Fingerprint configured DSH models without trusting their reported token counts: a 55-vector tokenizer reference, four greedy identity probes, refusal-prose and stop-vocabulary probes, and a local 18-item weighted intelligence battery scoring 0-100 with a tier and per-question evidence, plus animated or custom SVG and HTML drawing probes, quick SVG limits, concurrency controls, and latency and token metrics. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-workbuddy-theme
elegant01/dsh-workbuddy-theme
Recolours and re-lays-out the DSH Web GUI as Tencent WorkBuddy desktop does: mint brand #00c29a, gray sidebar, 24px composer with a single hairline border, 848px column. Values are read from WorkBuddy v5.0.2 asar tokens, not eyeballed; light mode only, pure CSS, restores by removal.
dsh-cache-monitor
vhow123/dsh-cache-monitor
Shows the current conversation's cache hit rate and per-request token details in a fixed DSH sidebar entry.
dsh-minimax-radar
themachinecorp/dsh-minimax-radar
Monochrome MiniMax Token Plan radar: a sidebar readout with the 5-hour and weekly window remaining and both reset countdowns, plus a dashboard with tokens spent on this machine by day and by model and the pay-as-you-go cost estimate.
dsh-man-031
gongfpp/dsh-man-031
Shows a Kobe iced-tea side popup and reports per-turn costs or token counts with bundled offline audio. Uses dsh-cost-meter first, or estimates each request from native usage and public prices. Includes twenty cost phrases, four token phrases, CNY/USD, three-decimal rounding and custom previews; no runtime TTS service or API key. The bundled voice clips are pre-synthesized offline and the portrait is a fan-made image; the package declares UNLICENSED. When it has to estimate a cost itself it fetches a public price table from raw.githubusercontent.com (Han-1413141/dsh-cost-meter) and the USD/CNY rate from open.er-api.com, at most once a day, and sends no session data.
dsh-deepseek-usage-extended
elsebit/dsh-deepseek-usage-extended
A fork of dougen/dsh-deepseek-usage (the upstream repository has no license file; its manifest declares MIT) that adds IKunCode account balance queries alongside the upstream provider readers, subscription usage windows and model price snapshots. For IKunCode, your key is sent as a Bearer token to api.ikuncode.cc. It installs as @elsebit/dsh-deepseek-usage-extended from GitHub Releases with its own routes and settings, so disable the original usage plugin if you want a single card; the OAuth credential references it inherits are shared with the original.
dsh-balance-spend
bluuuuuuuuuuuuuuuu/dsh-balance-spend
Account balance chip beside the Harness mark, per-session spend beside each Session row, and a sidebar-foot list of what running sessions are spending — all priced from each session log's token usage, with a live ≈ estimate while a call is streaming.
dsh-whale-balance-pet
xinchen262/dsh-whale-balance-pet
A floating whale-girl pet for DeepSeek Harness that shows the live account balance and per-minute token spend.
Hardworking-donkey
lisusuba/hardworking-donkey
A full-viewport donkey-mill background for the DSH Web UI: an animated top-down donkey or a Chinese-character form circles the millstone, accelerating with the model's live token throughput and plodding slowly when idle; a bottom-right panel switches form, adjusts opacity and hides the scene, persisting in localStorage.
dsh-token-ledger
yinshipeng/dsh-token-ledger
DSH plugin: lifetime token counter in the conversation header, summed across every local session.
dsh-power-menu-web
dddmuc/dsh-power-menu-web
给 dsh web 部署加一个右上角电源按钮:刷新 / 重启 / 定时 / 关闭。重启后自动把新 token 的链接打开——dsh web 每次启动都换 token,不打开就得自己去日志里翻。macOS 走 launchd、Linux 走 systemd、其它平台自己 respawn。
dsh-web-control
weichengwu/dsh-web-control
Manage a LAN or Tailscale reachable dsh web instance from inside DSH. dsh web listens on loopback by default; this adds a Settings > Web access panel that detects the machine's Tailscale and LAN addresses, starts dsh web bound to the one you pick, and shows the token URL to open on a phone or another machine. Also stops and restarts it, tails the child log, persists the bind address and port, and registers two agent tools (dsh_web_control, dsh_web_config). Zero runtime dependencies. Anyone who can reach the bound address and holds the token URL gets your dsh's full privileges (files and commands); LAN mode is plain HTTP, Tailscale is encrypted by the tunnel, and the token is single-use and changes on every start.
dsh-job-board
shaot92-del/dsh-job-board
Multi-machine job board for DSH: 14 board tools, 4 shell tools, a GUI panel, and a dispatcher that hands queued tasks to remote hosts through dsh-remote-agent. Pick the target machine and model from the panel or the board_options tool; rename machines with display aliases while task ownership stays keyed to the host identity (machine). Failed tasks can be retried with their original goal/workspace/model, and the panel checks npm for a newer plugin version. Single-machine use starts its own loopback board; multi-machine use needs the bundled Python board server (tools/board_server.py, started with GP_BOARD_TOKEN set, binding 0.0.0.0 by default) and dsh-remote-agent hosts. The sh_* tools only reach directories on the allowedRoots list.
dsh-thinking-channel-guard
laoyingfuhuole/dsh-thinking-channel-guard
Moves reasoning that a provider leaks into the visible text channel back into the reasoning channel, and emits a text block when a whole turn of answer text lands only in the reasoning channel. Catches three shapes: `<thinking>`-tagged text, text that continues a reasoning tail which ended mid-token, and an answer-only reasoning turn that stops. Healthy streams pass through unchanged, block order is preserved, and each of the four rules can be switched off in one JSON config.
dsh-repot
daoyan2142/dsh-repot
Carries a DSH environment between machines through one private GitHub or Gitee repository: third-party plugins (reinstalled from a version, or carried as a tarball or source tree), the four profile configuration files, and folder snapshots. A restore resolves each folder through an absolute path, a registered root, or a confirmed new path, compares file by file, leaves locally edited files alone, backs up anything it replaces, and refuses writes that escape a root, cross a junction, or land on a directory the plugin does not own. Configuration files and folder contents are uploaded as they are (no secret scrubbing) and the plugin does not check that the repository is private; the access token stays in the credentials service, and on first start a GIT_SYNC_* token left by dsh-plugin-git-sync is copied over. Needs Node 22.12 or later.
dsh-github-trending-masonry
zhang-eli/dsh-github-trending-masonry
GitHub Trending masonry feed in the DSH sidebar: daily, weekly and monthly boards with category chips, concise project intros, and one-click starring that syncs to your GitHub account or saves to a local collection. It reads github.com and raw.githubusercontent.com, sends README excerpts to your current model and text to Google Translate when a translation is needed, and stars with the GitHub token you connect (or GITHUB_TOKEN / GH_TOKEN); its HTTP routes have no DSH access check.
dsh-voice-dialog
qinfpv/dsh-voice-dialog
Continuous voice conversation for DSH: auto sentence splitting, a 2-second confirm window before sending, and spoken replies you can interrupt by speaking. Speech is recognised by DSH's own speech service by default (a local Whisper bridge or an OpenAI-compatible endpoint can be set instead), the recognised text is corrected by a DSH model call, and replies are read aloud through Microsoft Edge's online text-to-speech service, so reply text is sent to Microsoft. A daily check of PyPI and Hugging Face for faster-whisper updates is on by default; settings and any API keys are stored in plain text in ~/.dsh/voice-tutor-config.json. Its /voice-tutor routes require an authenticated DSH session (admission is checked per request), API keys are never returned, and applying an update needs a one-time confirmation token.
dsh-playwright-mcp
cqin04/dsh-playwright-mcp
Configuration bundle that connects Microsoft's official @playwright/mcp to your running Chrome through the Playwright extension, so the agent can drive your logged-in tabs. Install from a local copy: put your extension token in cordis.patch.yml first (with the token, connections skip the extension's approval prompt, so keep it private). Needs Node.js and the Playwright Chrome extension; the default command is the Windows form (cmd.exe /c npx), so change it to npx on macOS or Linux. It starts @playwright/mcp@latest through npx.
dsh-Engram
yhprime/dsh-engram
Experience and skill engine with a sidebar console and exp_record / exp_recall / exp_feedback / exp_consolidate / exp_type tools, stored in a local JSON file. Optional Git backup (off until you configure a remote) pushes the library to a remote you choose; GitHub sign-in uses a device code or a token kept in local settings.
dsh-task-dispatch
vinson1101/dsh-task-dispatch
Dispatch a task to a real DSH session by workspace path or session id; results land in a persistent task ledger that can be queried without triggering the model. It serves HTTP on 127.0.0.1:7391 and requires a bearer token it generates on first run (kept in ~/.dsh/relay/token), rejects non-loopback Host and foreign Origin, and stores task results as JSON files under ~/.dsh/relay/tasks; an optional notifyUrl receives each finished result.
dsh-compaction-vcc
tingfeng-droid/dsh-compaction-vcc
Replaces LLM summarization with deterministic text compilation, so compaction makes no model calls and keeps original tokens; elided content stays retrievable through seq pointers. Based on TsFreddie/dsh-compaction-instant.
dsh-session-fold
kennethfan/dsh-session-fold
Folds older oversized tool results into spill files and replaces them with short, deterministic stubs at step boundaries, with no LLM call: the stub keeps the first 200 and last 80 characters plus the sequence number, tool name, line/char/size counts and the original file path, and each fold is a real surface replacement accompanied by compaction/prune shadow pricing so token counts stay honest. Triggers on context pressure at 25% of the model window (falling back to 32768 tokens when the window cannot be resolved) or on five accumulated candidates; the last three turns, error results and rich content are never folded. The original is recovered from the session log rather than the spill file, so /folds, /unfold <seq> and /unfold all keep working after spill cleanup; session_fold_recall lets the model fetch a folded result by sequence number or by keyword, and session_fold_diagnose reports the effective settings. /spill-prune removes orphaned spill directories, preview only unless --apply. A Settings page exposes 12 of the 13 options as draft-then-save fields; they are volatile, so saved changes apply without restarting the plugin.
dsh-context-domains
guicaiyue/dsh-context-domains
Puts a domain bar under the session header — a domain groups skills and tools and toggles as one block, so one click loads or unloads every member. Hovering a chip lists its members (skills, then tools) in a height-capped panel that scrolls. The right end of the bar is a compaction-threshold counter (− 5 +, 100k tokens per step) that rewrites the live compaction engine policies, so the compaction trigger line changes on the next turn without restarting dsh; a degraded fallback turns the number amber and is reported in the snapshot. Settings maintains domains and members with search, skill/tool tabs, all/selected/unselected filters and a copyable AI grouping prompt. Tool removal uses tools.restrict plus a guard; hiding a skill re-registers it with modelInvocable false, so it leaves the model catalog while /name still works. Sessions of another preset are left untouched.