Плагины

Упорядочивает сессии workspace DeepSeek Harness, переименовывая их как «категория｜тема» и выдавая рекомендации по архивации, переименованию и проверке.

Используйте подписки ChatGPT/Codex в DSH, с поддержкой генерации изображений и веб-поиска.

Веб-приложение для просмотра файлов для DSH: интерфейс React и REST API, обслуживаемые хост-веб-сервером, команда /dsh-agfs, открывающаяся в текущей рабочей области сессии, и инструмент модели browse_files.

Открывает возможности агента DeepSeek Harness как MCP-сервер, чтобы внешний MCP-клиент (например, Hermes) мог управлять Harness для выполнения задач по написанию кода. Hermes = мозг, Harness = руки.

Запуск расширений Pi как плагинов DeepSeek Harness в рамках агента

Совместимый с Symphony оркестратор задач с несколькими провайдерами и дашборд для DeepSeek Harness

Стабильная, редактируемая генерация PPTX для AI-агентов — на входе семантическое промежуточное представление, на выходе нативный DrawingML

Ship DeepSeek Harness to your own VPS: one command (or a form in DSH Settings → VPS Deploy) installs a zero-dependency login gateway, automatic HTTPS through Caddy, systemd supervision and one-click DSH upgrades.

Keeps a project's documentation in step with its decisions on DeepSeek Harness: the same append-only decision log and derived design snapshot, kept fresh in-process instead of by a hook process.

Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.

Live2D session view with realtime voice: continuous voice input, streaming TTS, subtitle translation, multi-model catalog, standalone entry / Live2D 实时语音会话视图：连续语音输入、流式 TTS、字幕翻译、多模型目录、独立入口

One-command VPS deployment for DeepSeek Harness: a zero-dependency login gateway with automatic HTTPS that proxies the native web UI, a token-protected setup wizard, and one-click DSH upgrades with automatic rollback; as a plugin it adds Settings → VPS Deploy with version, upgrade and gateway status, or the one-command setup when DSH is not yet on a VPS.

Deterministic project actions shared by people and agents: one actions.json, a right-sidebar run panel, and agent tools.

Meeting rooms for DSH sessions: joining a room grants the right to convene and the duty to attend, and a session belongs to at most one room. Convening forks each participant in with its own completed-turn context and with its tools stripped, a moderator that carries no context chooses the speakers, and every turn is appended to disk as it is spoken. After adjournment each participant receives its own minutes as a user turn and resumes work.

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics, and verifiers.

DSH plugin: shows the DeepSeek account balance at the bottom of the sidebar, with a configuration card in settings.

Adds an Explain button to the approval card: one model call returns exactly three lines reading the pending operation, covering what it does, which files or system state it reads, writes, modifies or executes, and a risky/attention/safe verdict with a one-sentence justification. It also renders the detail area for `write` and `edit` calls, which the shipped renderer leaves blank because it only reads a `command` field.

TypeSafe Jev (решающая модель System One) для DeepSeek Harness, от начала до конца: jev_decision (choice/score/noul, параллельно, типизированные ответы + уверенность), карточка Settings > Plugins для API-ключа и переключателей, встроенные представления инструментов, показывающие каждое решение в диалоге (ответ, уверенность, задержка, стоимость), авто-защита (детерминированные проверки + проверки риска и циклов от Jev), локальный дашборд /jev и онлайн-бенчмарк верификации (96.3% на 27 размеченных вопросах, медиана ~283 мс на jev-latest, 2026-09-21). Честность по замыслу: только реальный API, без mock-заглушек.

Animated DSH Web pet with model-adaptive output pacing, tool-state reactions, replaceable character packs, and a bundled skill for creating or extending pet animations.

Blocks an agent from reading, searching, writing, or editing chosen files and directories, keeping their contents out of the conversation — including sensitive-word files whose text can make later provider requests fail with a 400. Rules are picked from a file/directory browser on the plugin page.

Fronts stdio MCP servers with three router tools (list_capabilities, describe_tool, call_tool) so schemas load on demand instead of riding every request; shapes every tool result through a deterministic output ladder that archives the original first (retrieve_spill reads it back); prices tool groups in tokens and can hide built-in groups per agent. Bridges to a standard-library Python router, so Python 3.9+ is required.

Simulated life context for DeepSeek Harness: every turn injects the past 24h of simulated life events from the workspace .life/ directory (sliding-window filter, session-level deduplication with delta updates, world summary) as a collapsed context notice, and the life_react tool lets the agent record feelings, thoughts and actions back into its life log for the next round of world evolution — turning a DSH agent into a roleplay character with a persistent daily life.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.