Plugin

One hub over every coding IDE you run — dsh, Claude Code, Codex, ZCode, Qoder, CatPaw, Trae, OpenCode. Zero-API: it reads each tool's own on-disk state and gives a session inventory, per-IDE usage with cache-hit rates, one-line resume commands, and a single .hub/ rule body wired into all eight via marker-delimited pointer files. The domestic-IDE adapters (Trae/Qoder/CatPaw) were verified against the installed binaries — a gap no overseas tool covers.

Shows what each completed turn cost in CNY on its own row under the turn, with a click-to-open breakdown naming the tokens per category, the unit rate, the matched price rule and the billing instant; per-model rates are edited on a settings page inside DSH — four token categories plus weekly recurring peak/valley rules with arbitrary multipliers and absolute time-window promo prices that override them. 0.2.3 adds account awareness: it reads the balance or remaining quota of 14 providers (DeepSeek, OpenRouter, Zhipu GLM, Moonshot, MiniMax, Kimi Coding, OpenAI-compatible relays and more) and shows today / this month / this session spend next to it; spend is accumulated in a local ledger (atomic writes, one book per API key, 1-24 month retention, JSON export), and a monthly calendar lets any day be corrected by hand - including days with no balance observation - with an optional note. Usage and rates are computed locally from what the provider reported; balance is read straight from the provider API with your own key, and nothing is sent to a third party.

Memory-assembly team for DeepSeek Harness: every message triggers a five-step cognition loop (judge, retrieve, assemble, feedback, calibrate) carried by role-playing subagents (judge, retriever, archivist, advocate, editor, scribe), using BM25 retrieval, time-ordered material, and LLM assembly to build useful material packs injected into linghun. Works with dsh-linghun.

A chip at the left end of the composer tool row showing whether DeepSeek bills at peak or off-peak right now. Clicking it opens a card with the current state and rate, the next switch with a countdown, and why this instant is in that state: a weekend, a named statutory holiday, a 调休 make-up workday, or simply outside the peak windows. Times are resolved in Beijing time with an explicit UTC offset, so the verdict does not depend on the machine clock; a hard-coded 2026 Chinese holiday table carries the 33 holiday days and the six 调休 workdays, and a year beyond the table says so instead of guessing.

Mostra fasce di riempimento del contesto, soglia di compattazione per sessione calcolata dalla finestra del modello, costo per passaggio in base alle tariffe di lettura e scrittura della cache, cache hit, saldo DeepSeek con tariffe di punta e fuori punta e passaggio di consegne con un clic. Non chiama modelli e non consuma token.

Exposes the models already configured in DeepSeek Harness through an OpenAI-compatible gateway, so other local projects can call them with any standard OpenAI client. Multiple provider candidates share one named group with ordered, balanced or random dispatch; upstream failures before any output switch to the next candidate transparently, and rate-limited requests are retried after the provider's backoff. Per-candidate call statistics (attempts, answers, failures, token/TTFT totals) appear as badges in the settings page, and daily aggregates persist to a local file with a 30-day heatmap and trend view. Until you create a key in the UI, the endpoint accepts calls from anyone who can reach it; keys (stored as SHA-256 hashes) then turn authentication on, and the endpoint stays locked even after the last key is revoked. Exposing the optional LAN listener without a key leaves the port open to the whole network. Runs on DSH 0.1.2-rc.1 through 0.1.7-alpha.1 and later.

Run one instruction on every online Windows and macOS machine, across networks and regions: a dependency-free relay talks to each machine over outbound connections only (Tailscale, a public VPS behind TLS, or a tunnel), every machine runs the command in its own checkout, and results come back with a commit, a working-tree fingerprint and a command hash so an environment mismatch is reported as unverifiable instead of being mistaken for a different result. Sending work needs its own operator token, separate from the per-machine device token.

Think tank: a built-in library of 161 classic mental models (decision/strategy/cognition/psychology/communication/learning/system/innovation/execution) — enter one question and several selected models analyze it in parallel via AI, producing a synthesized report with consensus, disagreements, blind spots and an action checklist; supports both automatic analysis and prompt round-trip import.

Windows 2000 desktop skin for the DSH Web GUI: metric-accurate grey chrome, two-tone gradient title bars, 1px bevels, square corners, 16px scrollbars, and the pixel font it renders with served by its own host route.

Plugin DSH che registra la skill ai-eight-honors-eight-shames: otto regole verificabili per agenti di coding (verificare prima di chiamare, chiarire ambiguità, citare prove, riutilizzare prima di creare, testare prima di dichiarare concluso, seguire convenzioni locali, separare fatti e inferenze, mantenere reversibili le modifiche), più una nona che registra ogni richiesta e modifica nei report alla radice del workspace.

Pannello di chimica per DSH Web. Disegna strutture in Ketcher; uno script scarica la build, renderizzata localmente nel browser senza backend. RDKit calcola la molecola corrente senza chiamate al modello: formula, masse, logP, TPSA, donatori/accettori di legami H, anelli, Fsp3, centri stereogenici, controlli Lipinski/Veber, QED, avvisi PAINS/BRENK, scaffold Murcko, ricerca SMARTS, similarità, conversione, standardizzazione e pulizia batch. La scheda retrosintesi usa un backend sostituibile (Retro* per default) tramite processo JSON in/out e segnala cosa manca se non installato, senza inventare percorsi. I calcoli sono eseguiti dal pacchetto Python del repository (rdkit), da installare separatamente con pip.

Inbox personale per gli appunti in DeepSeek Harness (dsh): /inbox nel composer o pannello laterale salva link, immagini, testo e credenziali in un vault locale. Classifica prima con regole locali, poi con un modello a frequenza limitata; consente consultazione, ricerca e modifica. L'assistente recupera le voci su richiesta in chat; i segreti sono cifrati a riposo. Sync opzionale di voci e allegati via WebDAV/S3. Per ora solo Windows.

Genera immagini tramite una sessione ChatGPT web con accesso effettuato e le scarica in una directory locale.

Pacchetto strumenti FDE: un solo plugin installa una selezione di plugin dsh comuni (server Git, mount WebDAV, knowledge base, attività pianificate, ripresa automatica, ritocchi UI, retrospettiva automatica, file manager, titoli intelligenti, bacheca attività, mercato, riduzione del contesto, ponte IM e barra laterale). Un pannello mostra lo stato e colma le lacune con un clic.

Image and video production toolkit for DeepSeek Harness - background removal with quality tiers, local inpainting retouch, headline and logo compositing, batch platform-size exports and image QA reports; for video, AI subject matting with background replacement (RVM ONNX, plus a chroma-key path), animated titles with fade/slide/typewriter/karaoke presets, 53 transitions with stylized variants, and light-effect and grading presets with LUT support, alongside footage inventory, accurate cutting, subtitle burn-in, music mixing and platform-spec exports; it provisions its own local Python runtime through a bundled bootstrap script.

Integrazione Feishu (Lark) per DeepSeek Harness: 25 strumenti per messaggi di chat e cronologia, documenti cloud (incluse pagine di knowledge base, grafici e immagini generati), record bitable, intervalli di fogli di calcolo e permessi Drive, usando la tua app Feishu aziendale auto-costruita.

Generate and format Chinese Word (.docx) documents from a simple markup file, using built-in heading styles, SimSun and Times New Roman fonts, and per-chapter figure and table captions.

Process management: brings ntd-style processes (multi-stage, multi-step agent workflow templates) into the dsh web UI — browse, edit, validate, import/export and AI-generate processes; the built-in library is read-only while the personal library is writable with live file sync, and agents read the library through process_* tools and advance work stage by stage.

Render GeoJSON or vector data into an interactive GeoLibre map in a sidebar tab, and let agents operate the live map through tools: layers, styles, view, feature identification, GeoLibre processing algorithms, and the Whitebox toolbox (WASM in the browser).

Assistente vocale per DSH Desktop e Web GUI (stesso plugin, cambia solo il nome profile): pallina di chiamata trascinabile e VAD nel browser inviano ogni frase dopo una pausa. Riutilizza il modello locale SenseVoice già scaricato dal plugin ufficiale voice-input, senza scaricarne un secondo. Supporta FunASR HTTP/streaming, API compatibile cloud, MiniMax / MiMo-V2.5-TTS (director mode e voice clone) e risposte TTS compatibili OpenAI. Wake-word/auto-sleep opzionali e invio a sessioni separate con avanzamento, arresto e resoconto vocale.

Porta in DSH la base di conoscenza del codice di langchain-ai/openwiki: crea/legge/aggiorna con un clic il Wiki del repository, offre schede Grounded Claims con fonti tracciabili e una base di progetto da file locali caricati. Riutilizza il modello già configurato in DSH, senza una seconda chiave API.

Esperto in confronto e proposta di prodotti assicurativi — analisi delle clausole, rapporto costo-efficacia, pianificazione della copertura, genera proposte PDF verificabili rivolte al cliente.

Automazione desktop Windows per DeepSeek Harness: ciclo observe/act con priorità all'accessibilità e 30 strumenti standard (target elemento/coordinata, instradamento strategia auto/a11y/event), semantica di sicurezza con osservazioni sostituite e senza replay, interruttore di spegnimento persistente, protezione da obsolescenza RuntimeId/rect-drift, schede chat e pannello flottante (operazioni live, muro di frame, impostazioni di auto-rilevamento ambiente), descrizione visione a piastrelle per modelli a bassa risoluzione, registro di audit JSONL e lista di autorizzazione pid. Richiede Windows 10+ e Python 3.9+ con uiautomation e pillow (installabili dalla pagina delle impostazioni).

Analizza PDF di e-fatture cinesi (prima l'allegato XML, poi fallback con regex sul text-layer) in JSON strutturato con verifica incrociata degli importi, e genera report spese (Markdown / xlsx).