Плагины

Бесплатное зрение для текстовых агентов: встроенная цепочка распознавания без ключей API плюс пиксельные инструменты (вопрос-ответ, grounding, обрезка, попиксельное сравнение, цвета, OCR, трассировка в SVG, вырезание, скриншоты); просто вставьте изображение.

Free, keyless web search for DSH: 7 engines (DuckDuckGo/Bing/SearXNG free + Exa/Perplexity/DeepSeek paid), auto-failover, settings-page UI with API key inputs and official links, web_fetch, and an engine test tool.

Multi-engine fused web search, page fetch, real-time X (Twitter) search with credential-free fallback, deep research and parallel multi-agent research for DeepSeek Harness. Free layer: Bing / DuckDuckGo / Yahoo / Exa MCP (all keyless, live-probed); api la

Free vision bridge and image generation for text-only models: paste-image reading, GLM-4V-Flash and Gemini engine failover, ModLens-style structured evidence, and a seeded free vision model route.

Плагин тем для DeepSeek Harness: предложения тем на основе OKLCH + дизайнер тем (сохраняется между перезапусками).

Reads assistant replies aloud via free Edge TTS or your own RVC voice models: read-aloud buttons + auto-read, adaptive chunked progressive playback (gapless long reads), one-click voice-pack installs from a registry, and a portable RVC runtime.

Движок сжатия без потерь* и без участия LLM для DeepSeek Harness

Cross-platform Computer Use for DeepSeek Harness: virtual-mouse human-like operation (screen_observe + computer_click + type + key + scroll + drag, 11 tools), AX-tree zero-vision-cost mode with free GLM-4V-Flash vision fallback, safety guards (snapshot TTL / app whitelist / dangerous-action approval / password-box protection).

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

Seven video tools (probe/cut/concat/encode/subtitle/extract/gif) on the official subprocess service: shell-free argv, zero runtime dependencies.

Размещённый бесплатный vision-компаньон для DeepSeek Harness с устойчивым хранением доказательств по сессии

Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.

Mounts the hosted Exa search MCP endpoint (https://mcp.exa.ai/mcp) through the in-box @deepseek-ai/dsh-mcp-client bridge: web_search_exa and web_fetch_exa tools, anonymous on the free tier or with your own EXA_API_KEY.

Инструмент погоды для DeepSeek Harness: текущие условия и прогноз на несколько дней через Open-Meteo (бесплатно, без API-ключа).

Переключатель моделей для DSH: направьте его на любой совместимый с OpenAI эндпоинт, с подобранными бесплатными/дешёвыми пресетами провайдера DeepSeek и автоматическим резервным вариантом, если бесплатный уровень ограничивает частоту запросов.

Одно общее хранилище Obsidian для всех агентов: ядро на Python без зависимостей (search/promote/adjudicate/forget), шаблон хранилища, плагин dsh (memory_search/show/submit/status).

OpenCode Zen free models provider for dsh

DSH web port manager plugin: list all local listening ports, pick a free one, and hot-switch the DSH web port without restarting the process. 端口管理插件：查看本机已占用端口并热切换 DSH web 端口。

Rules, commands & skills manager for dsh: /rules slash command, settings panel with visual rule editing (add/edit/disable/delete, free-zone support), user-defined custom commands with {input} arguments, skill management, and automatic backup & one-click restore of AGENTS.md.

Voice pair: free edge-tts neural speech synthesis + OpenAI-compatible ASR transcription.

Native vision capability extension, using either Zhipu (free) or Qwen-VL (local).

Full vision-capability bundle for DeepSeek Harness: a vision_understand tool (OpenAI-compatible vision APIs, free Zhipu GLM-4V-Flash by default) plus paste/drag-and-drop/button entry points for image recognition.

Free vision bridge for text-only models: image understanding, OCR, UI and debug analysis via free-tier providers (Qwen3-VL-Flash, Doubao, DeepSeek-OCR) with a settings GUI.

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.