Plugin

AI provider runtime and configuration UI for shared credentials and embedding, reranking, speech, and image generation services in DSH.

Per-request cost ledger covering retries and subagents, holiday-aware peak/off-peak pricing, shared pricing/usage/balance/budget services, and DeepSeek bill reconciliation.

Invites people into one conversation through single-use links with no account: up to 20 guests discuss together and ask the AI, the shared fork runs read-only, and the owner can remove guests or end the share at any time.

Connects dsh to the GreatArrow.ai MCP server over Streamable HTTP, so the agent can search and save workspace memories, tasks and decisions shared with your other AI clients; a config-only bundle that reads the token from great-arrow.token in the dsh home, never from the environment.

Connects DSH to shared multi-agent rooms on roomcomm.xyz through a remote MCP server and a coordination skill.

Full edition of the motor-design AI plugin for DeepSeek Harness: adds the L1 (Ansys RMxprt) and L2 (Motor-CAD) precision layers on top of the L0 millisecond-level broad filter, completing an end-to-end chain from requirement parsing to parameter identification, candidate matrix, L0 pre-screening and L1/L2 verification. Mutually exclusive with dsh-motor-ai-l0 (uninstall l0 first); the shared core @wangxue98/dsh-motor-ai-core installs automatically. L1 needs Ansys AEDT (RMxprt) and L2 needs Motor-CAD installed locally. Distributed under the PolyForm Noncommercial licence; L1/L2 require an activation code. Telemetry is on by default: per-tool usage counts and design-experience samples that the author describes as desensitized are sent to the author's server at wangxuewangxue98.deno.net, and fault assistance can upload fault reports; switch them off with telemetryEnabled, designExperienceUpload and faultAssistEnabled in the plugin config.

Ops request channel for a team over Feishu DMs — a colleague's message waits in a serial queue behind an approval card that the paired admin must accept, then runs in one shared DSH session with a persona attached, and the answer is posted back to the requester.

Shared infrastructure for data assetization plugins: business rules loader, file format adapter, report generator, path validator, audit logger Also known as @deepseek-ai/dsh-data-asset-shared.

Connects DeepSeek Harness to the QianYuan MCP server, a shared record of pitfalls other agents already hit and results they already produced, plus capability lookup. Exposes 13 tools named mcp__qianyuan__*. Reads are open and need no key.

Persistent personal todos shared across DeepSeek Harness sessions and projects: SQLite storage, Agent tools, a native sidebar and turn-tail cards, with user-managed workflows or optional dispatch of individual todos to Agent sessions.

Seven shared engineering skills, a read-only project dashboard with amendments, options, stages and SQLite audit browsing, and workflow request previews for DSH.

Coordinates bounded project recall from compatible memory and learning providers, with shared settings and provider lifecycle management.

Embedded dsh bundle for dsh-plugin-ops: a settings-page health panel (scan, plugin rows, diagnosis chat) over the shared engine

Authored pull request feedback inbox with paginated GitHub collection, priority favorites, and version-bound local progress shared by the DSH panel and CLI.

Software Atom Market for DeepSeek Harness - lets agents browse a shared store of contract-typed capability atoms: search atoms, read full manifests, validate submissions, draft new atoms (atom_search/atom_read/atom_validate/atom_draft); GitHub store as zero-config default source.

Auto-approval agent for DSH permission requests: rule layer (denyAlways/allowlist) plus Hermes Pro semantic adjudication with quick-fail retries, fail-closed to human when Hermes is unavailable, rejection feedback returned to the requesting session, and approve tasks enqueued into the task queue with a shared busy mutex.

dsh port of the shared handoff kit: handoff and task-id-bootstrap skills plus host-side automation — baseline state injection, per-turn snapshots with an Auto Log trail, task=<id> routing, continuation re-injection, a compaction guard with clear-required alerts, and read-only subagent handling — all writing the same .agents/state/ as the Codex, Claude, and pi editions for one-repo multi-agent handoff.

Plugin Web DSH con chat laterale persistente basata su fork e bolle di annotazione condivise in stile Codex tramite dsh-annotation-core.

Memoria a lungo termine curata e basata su file per DeepSeek Harness: note Markdown leggibili e un unico store di file semplice condiviso tra host (git-ignored se dentro un repository di progetto). ctx.tools.guard() impone un limite deterministico all’indice.

Flashcard di vocaboli durante l’attesa dell’agent: dopo ~18 s di attività appare una scheda di ortografia nell’angolo in basso a destra del client Web e scompare a fine sessione o quando serve input. Condivisione facoltativa dei progressi con l’app desktop VibeGap locale.

Riconcilia estratti conto, fatture e registri che devono quadrare. Converte PDF di estratti bancari/di credito e lotti di fatture in tabelle pronte per il libro mastro; riconcilia con una chiave condivisa in centesimi interi o, senza chiave, per importo e intervallo di date.

Condivide qualsiasi sessione DeepSeek Harness come pagina Web statica autonoma e di sola lettura: timeline, chiamate agli strumenti e ragionamento comprimibili, mascheramento predefinito dei dati sensibili, due impronte SHA-256 e filigrana.

Aggiunge un workspace predefinito differito basato su una directory di lavoro condivisa e configurabile.

Usa un browser Playwright condiviso con l’IA di DeepSeek Harness.