Plugins

Realtime WebGPU ocean skin with quick controls for waves, daylight, glass opacity, and an automatic day cycle.

Capa de ejecución consciente de la GPU para DeepSeek Harness: herramientas gpu_status / gpu_exec / gpu_run_bg, inyección de contexto de GPU por paso, y selección automática de tarjeta mediante CUDA_VISIBLE_DEVICES

Backend de memoria vectorial y de grafo: herramientas observe/remember/search/recall contra un servidor memoria local, que fusiona la recuperación semántica HNSW, la búsqueda por palabras clave FTS5 y señales de grafo de conocimiento mediante ranking RRF, con persistencia automática al final del turno y aislamiento de espacio de nombres por agente.

WeChat ClawBot/iLink channel plugin: QR login in DSH Web, message send/poll/status tools, background polling, and optional per-sender persistent DSH sessions that automatically reply through WeChat.

DeepSeek Harness (DSH) plugin for local-first automatic Wiki memory and native Skill generation.

MsgRail（消息轨道） —— DeepSeek Harness 的窄消息轨道插件：在对话左侧，为每条你发送的消息显示一根细横线。悬停看预览、点击即跳转，更早消息自动加载；全量历史、实时更新、中英双语。 MsgRail is a narrow message rail for DeepSeek Harness: one thin bar on the left of the chat for each message you sent. Hover to preview, click to jump — older messages load automatically. Full history, live, bilingual.

A DeepSeek Harness web plugin: set a background image and adapt the UI's text, background, brand and border colors to the image palette automatically.Built with DeepSeek Harness

dsh auto-vision bridge: paste an image into a text-only model's composer and a configured multimodal model transcribes it as text, automatically.

Record & Replay for the dsh web GUI: (1) replay every automatically recorded session as a readable timeline, export/import shareable replay packs, re-run a recorded conversation; (2) Codex-style screen recording -> skill generation - record a computer-use

Codex-style code and file selection for DeepSeek Harness Web: workspace file tree + file viewer; selecting code or a whole file adds it to the message as context automatically

DeepSeek peak-pricing cost guard for DSH: during peak hours (Beijing 09:00–12:00 / 14:00–18:00, ×2) the agent automatically switches to ultra-compressed caveman-style output to save tokens, and a header badge + toast keep you posted on every peak/valley t

Automatic and user-customizable Fluent-style icons for DSH Settings and sidebar actions, with offline SVG packs and original-icon preservation.

Perseus Vault memory plugin for DeepSeek Harness: automatic pre-step recall injection from a governed memory vault

Live CVE/supply-chain audit for your workspace's own project dependencies (npm/pip/go), backed by OSV.dev, with a `cve_audit` tool plus optional automatic re-scan on lockfile changes.

Automatic secret redaction in tool results: masks API keys, tokens, JWTs, private keys and configured secrets before the model sees them.

Evidence-backed Skill self-evolution for DeepSeek Harness: redacted trajectory learning, quarantined proposals, arena validation, canary monitoring, automatic rollback.

Two-way Feishu (Lark) chat bridge for DeepSeek Harness over the official WebSocket long connection: messages route to the bound workspace's latest session and replies return automatically; bot credentials and workspace routing are configurable from the settings page.

Multi-workspace sandbox: grants file-write access to every registered workspace automatically — add a workspace, write to it immediately, no config or escalation needed.

DeepSeek Harness automatically opens browser plugins and includes a built-in WebView2 program to achieve a lightweight desktop experience.

Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions, with automatic context injection, archive on clear, and an optional web panel.

Automatically starts a fresh Web session near the context limit with the last complete turn, and adds an editable additive whale-maid persona with on-demand reload.

Automatically fills in reasoning-effort levels for models from unofficial (custom) providers, with data sourced from models.dev.

Automatic provider failover on rate limits or quota exhaustion: switch between providers with configurable per-provider models, a cooldown, and a permanent last-entry fallback.

Un kit de seguridad para el desarrollo: instantáneas continuas de configuración, reversión automática ante fallos de plugins, rescate en caso de fallo de arranque, y un panel de gestión dentro de ajustes.