Plugins

DeepSeek Harness 提示词破限插件：通过系统提示词解除模型回答限制，深度适配 Web 与桌面端多模式及工具调用

Rhine Lab-style boot animation for DeepSeek Harness: six acts from a black title plate through irradiated white-out to a warm dossier panel, five access-authorization steps (the first two can wait for a click or Enter, and Esc skips), real-voice recordings for the first five lines, and a settings page that switches between warm-light and dark themes and live-edits 33 playback, identity, voice and visual options.

A purely plugin-based implementation that brings "cross-session long-term memory + background self-evolution" capabilities to DeepSeek Harness: five-track memory · git branch awareness · in-turn self-review · skill self-evolution and skill manager · four-track to-do · COI scheduling · session broadcast · session search · prompt manager · temporary info notes—zero core modifications, zero runtime dependencies, ready to use upon installation and completely removable upon uninstallation.

Adds an editable conversation canvas to DeepSeek Harness, where graph connections select context for canvas requests, with branching, merging, and local agent session imports.

Lets the DSH agent operate your Windows apps and web pages: it reads controls through UI Automation, clicks, types, captures the screen and reads text with OCR, and works on web pages in its own browser in the background, without moving your mouse; when it needs your mouse or keyboard, an on-screen indicator appears and Esc stops it.

Parody ads in 2005-Chinese-web style: sidebar banners, in-chat feeds, corner popups, and a close button whose hit area is smaller than it looks. All fictional.

Chrome sidebar extension that lets DSH operate your browser directly, no vision capabilities required.

Give DeepSeek Harness a real office environment. Univer Office Plugin brings spreadsheets, docs, slides, canvases, relational tables, and more into one runtime — with connected data, validation, versioned changes, and isolated worktrees for multi-agent collaboration.

Visual, non-linear conversation workspace for DeepSeek Harness — sessions, follow-ups and branches become a browsable conversation map.

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.

AnySearch-powered real-time web and vertical search provider for DeepSeek Harness.

Per-session and daily API cost, budget with usage %, official balance, history dashboard, and one-click official price sync with peak/off-peak pricing.

White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.

Traceable, searchable cross-session memory for DeepSeek Harness — conversation knowledge as typed graph nodes (TASK/SKILL/EVENT) and typed edges.

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.

A browsable daily catalog of DeepSeek Harness plugins harvested from npm and GitHub: one-click install, enable/disable, update and uninstall, the reason dsh would refuse an install shown before you press it, prepurchase facts (engines.dsh, dependency count, bin names, install scripts), rollback and favorites.

Connects DeepSeek Harness to Avernet's Bot Collaboration Network over WebSocket V2, with automatic onboarding, isolated agent sessions, tool-call events, and multi-bot routing tools.

Lets a text-only agent watch a live screen or camera feed: every frame is scored by how much the picture changed, only the ones that matter are packed into one numbered sheet with an audio envelope, so the model looks at what actually changed instead of a screenshot every few seconds.

Connects dsh to a local SandBase Harness runtime over stdio MCP for managing agents and sessions, streaming turns, inspecting artifacts and cancelling work.

An editable diagram canvas in the DSH sidebar plus two agent tools (diagram_read, diagram_apply) that read and edit the workspace in place, using native .drawio files: the canvas opens and saves them losslessly — cells it does not understand are preserved byte-for-byte — and a file-fingerprint revision powers optimistic locking against concurrent edits.

Puts the agent on QQ as a persona character through SnowLuma (OneBot v11): private and group chat, voice notes, stickers, Qzone diary, Bilibili browsing, song covers, image generation, long-term memory and mood. Every feature is a module you can switch off, replace or extend locally — hot-reloaded modules can also rewrite group-reply decisions, prompts, outgoing messages and per-chat model choice. Safe by default (master switch off, dry run on).

2005 Chinese-web-style ad layer (joke plugin).

Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, with Settings login, model catalogs, usage, plus image_generate, video_generate, and x_search tools.