Plugins

OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.

Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.

An agent preset for evidence-checked research: every step advances only through system-verified observations, L3+ claims go to an independent evaluator, and the session folds into a replayable ledger that grows into a browsable domain ontology. Requires DSH >=0.1.7-alpha.1.

Brings the session history of nineteen other coding agents into DeepSeek Harness: recall, session digest and per-file history tools over a local index, plus optional automatic recall before each step.

Long-term memory for DeepSeek Harness kept as plain markdown, one fact per file, readable in any editor. The `MEMORY.md` index has a hard 200-line / 25 KB cap enforced by `ctx.tools.guard()`: a write that would grow an over-cap index is denied, while a rewrite that shrinks it always passes, so an oversized index can be compacted step by step. The plugin never writes memories on its own — what is kept is decided by you and the model. The same store is also used by Claude Code, Codex, Kiro and OpenClaw.

Let DeepSeek Harness see and operate any program on Windows. The model looks at the real screen and drives the mouse, keyboard and windows itself. It is fast: several steps run in a single round trip, and a window can be focused before input lands, so the click hits the right one. It can do anything you would do on a desktop, including but not limited to CAD drawing, circuit simulation, and sending messages.

Session minimap in the scrollbar gutter: to-scale bands coloured by event kind, anchor dots for user messages and failures, auto-loading history at the top, a hover wall of every prompt in the session, and a three-step map scale switcher.

Bioinformatics agent preset with 17 BioDSH analysis skills (single-cell, bulk RNA-seq, survival, regression, ANOVA), a 2000+ skill library searched by a skill_library tool, per-message skill selection and a time/step convergence guard.

One-click prompt enhancement in the composer — rewrites the draft into a structured prompt (role and goal, executable steps, output format, acceptance criteria, edge cases) with before/after preview, fill-back, and undo. Never changes intent, never fabricates requirements.

Novel-writing guardrails: 20 novel_* tools enforce fact-ledger consistency, phase and chapter gates, machine audit with deterministic metrics, and proposal-only revisions; a right-panel workbench covers reading, TTS playback, polish, proofread, continuity checks and batch drafting, and a bypass engine runs internal steps off the main conversation.

Twelve official Remotion skills synced from the official upstream (programmatic video with React: animation, audio, captions, 3D, maps, charts, render, Studio), plus a bundled-resource health check. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Views and builds CAD models (STL, OBJ, STEP, IGES, DXF, SVG) via cad_view/cad_info and OCCT parametric modeling tools, with an interactive viewer card and a resident CAD panel in the Web UI.

Injects a fixed system-reminder at the first step of every turn asking the model to reason and answer in Simplified Chinese, while code, commands, file paths, and identifiers stay in English.

IMAP/SMTP email tools (list/read/search/send/folders/attachment/health/watch/mark/reply) with since/until date-range filters, email_mark for read/unread/star/move, email_reply for reply/reply-all/forward with threading headers, QQ/163/126/Sina/Aliyun/Gmail/Outlook/iCloud presets, multi-account support, a send-approval gate, a web settings page and a whale-girl new-mail popup driven by the incremental email_watch checker. Outlook OAuth2 device-code login works out of the box through a built-in community client, and an account can still supply its own clientId instead. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Detects prompt-injection, jailbreak, and secret-leak patterns on the agent/pre-step, tools/pre-execute, and tools/post-execute seams with allow/ask/block tiers, sanitized defend/detection audit events, a defend_report tool, and a destructive-delete command guard.

Conversation navigator panel: turn-folded outline of the current session with per-step kind badges (assistant, tool, command, compaction, error), a hover bubble showing the full user question, a minimal mode that hides turn numbers for an all-badge view, keyword filter over user questions and assistant replies, click-to-jump with reading-position tracking, and load-earlier/load-all history paging. Host >= 0.1.2-rc.1; legacy hosts install @legacy/0.2.5.

Twenty-one official HyperFrames by HeyGen skills synced from the official upstream (HTML video authoring, animation, keyframes, audio/music-to-video, CLI, registry, slideshow, talking-head recut, website/product/PR-to-video, Studio timeline conventions and more), plus a bundled-resource health check. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Presentation skill and tools: one sentence or one document to an HTML slideshow plus editable PPTX, seven layouts (incl. quote and native PPTX tables), speaker notes (HTML S-key panel and native notes slides), five built-in themes, default theme/language config and bilingual support. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Long-term memory for DSH: conversations auto-distilled into atomic facts, scene summaries and a persona profile, with relevant memories injected before every model step. Zero-config out of the box — hybrid BM25 + vector retrieval, optional offline local embeddings, chat/work family separation.

A Claude Code-style reasoning-effort slider for the DSH Web UI: stepless drag, snap-on-release, a WebGL fire trail, and real, working thinking-effort control for any custom third-party model or provider.

Multi-platform API balance and usage dashboard for the DSH web GUI: balances for DeepSeek, Zhipu GLM, Kimi, StepFun, SiliconFlow, MiniMax, OpenRouter, Novita and xAI under the composer, estimated per-session and per-subagent cost with DeepSeek peak/off-peak pricing, automatic discovery of relays configured in DSH settings, and an optional draggable whale widget.

Anatomy panel for the Agent-Body organs: serves a live vitals dashboard at /anatomy inside the harness itself - organs, heartbeat, healing ledger, self-training counters and the real pulse stream - read straight from the runtime files rather than retyped. Host-only, no client bundle and no build step.

Per-call cache billing inside the context-meter popover: current step, round and session totals with hit/miss/output tokens and amounts, automatic Beijing working-hour peak/off-peak pricing, per-model rates, and third-party relays billed too.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.