Plugins

Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.

Install safety net for DeepSeek Harness: pre-install snapshots, one-click/automatic rollback, guarded boot, and incident reports that auto-trigger agent analysis. 中文: DeepSeek Harness 插件安装安全网（安装前自动快照、一键/自动回退、守护启动、事故报告自动触发 Agent 分析）。

Deep-read books and articles in five modes (quick, deep, knowledge map, Feynman, full book) with claim-evidence-data reports, Mermaid/XMind mindmaps, batch comparison, budget preflight, transparent background-job progress, and MD/HTML exports from URLs, files, or pasted text.

DeepSeek Harness (dsh) plugin for stock analysis, screening, and strategy backtesting across A/HK/US/JP/KR/TW markets

Enregistrements persistants de l'utilisation des tokens par session, et un tableau de bord dans les réglages avec répartition par fournisseur/modèle et une carte de chaleur d'activité sur 52 semaines.

Quantitative R&D toolkit for DeepSeek Harness — 46 tools across six domains covering market data, indicators, factor evaluation, walk-forward ML validation, risk, options, bonds and fund simulation, with an end-to-end research pipeline.

MCP bridge to gemini.google.com: vision analysis of images and videos, Imagen image and Veo video generation, and conversation management using the logged-in browser session with no API key.

Connectez plusieurs projets Overleaf à DSH via OverleafMCP pour la navigation, l'analyse et les mises à jour de fichiers basées sur Git.

Structural code intelligence for DeepSeek Harness — gives the agent codegraph and codegraph_index tools to find where a symbol is declared, what calls it, what a change reaches, and how one symbol reaches another, from a tree-sitter index it builds itself

Statistiques descriptives, percentiles, distributions de fréquence et corrélation.

Interactive candlestick cards for dsh web: market_snapshot and get_ohlcv results render as K-line charts with MA overlays, volume, and the indicator regime the model actually read

Exports metadata-only DSH turn, model, tool, approval, retry, and error events to Tuning Engines for governed traces, policy evaluation, cost analysis, and Work Session review, with a disk-backed retry queue.

DeepSeek Harness 原生视觉 Bundle：粘贴或拖入图片，通过托管的 deepseek-vision-mcp 调用 OpenAI 兼容视觉模型。

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.

Plugin de vision DeepEye pour DeepSeek Harness (DSH) : description d'image, OCR, VQA, mise en page d'UI et analyse du presse-papiers.

Un plugin dsh qui permet à l'IA d'invoquer automatiquement des VLM (modèles multimodaux) pour l'analyse visuelle.

Unified LLM request/response inspector: reasoning-effort tuning, external-think export, traffic & bundle analysis.

Community search, similarity analysis, and install/dedupe/build-it-yourself decisions for the dsh-plugin ecosystem.

Générez des rapports HTML interactifs autonomes à partir de Markdown, de tableaux, de graphiques, de cartes des provinces chinoises, d'organigrammes, de mathématiques et de tableaux avec exploration détaillée — un plugin DeepSeek Harness (dsh).

Plugin DeepSeek Harness qui relie les images de session à des API de vision interchangeables, tout en gardant DeepSeek comme modèle principal.

Analyse de vidéos Bilibili : métadonnées, transcription (repli ASR via Bijian/sherpa-onnx/whisper.cpp), commentaires, danmaku, et images clés nettes avec descriptions de vision locales optionnelles.

Bundled Xiaohongshu/RED viral-note agent skill: hot-note research, note generation/rewrite, verification, authorized account analysis, QR login and controlled publishing.

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

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.