Plugins

Regroupe les signaux d'arXiv, de laboratoires de première main, d'artefacts officiels, de fabricants de matériel et de X avec consentement en bundles de preuves versionnés, puis conditionne la reproduction au niveau de l'affirmation à des commandes, artefacts, métriques et vérificateurs.

Fournit l'outil bili_summary : métadonnées de vidéos Bilibili, chronologie des sous-titres et capture d'images avec sharp, avec gestion d'erreurs et dégradation gracieuse intégrées.

Explorateur flottant de l'arborescence de l'espace de travail pour l'interface web, avec coloration syntaxique numérotée et aperçu Markdown.

Voix pour DeepSeek Harness (dsh) — saisie par reconnaissance vocale + lecture à voix haute (TTS) pour DeepSeek texte seul, sans clé API.

Renomme les conversations de projet en titres clairs de type Catégorie｜Sujet, basés sur le contenu.

DeepSee : vision DeepSeek Harness, routage multi-modèles, et auto-vérifications visuelles Gemini avant livraison.

Profils de prompt Markdown réutilisables pour DeepSeek Harness, avec sélection du modèle par tour, substitution d'arguments et restauration d'état.

LESSONS.md (AI mistake notebook) visualizer panel for DeepSeek Harness Web UI — browse, search and review your AI mistake notebook entries by level and recurrence.

Role-based subagent delegation for DeepSeek Harness: one delegate tool over a folder of role files, with a roster that ships and stays overridable

Native headless and visible Chromium browser automation agent for DeepSeek Harness with DOM tree extraction, screenshot capture, and built-in SSRF protection.

Persistent long-term memory for DeepSeek Harness: a JSON store of typed entries (fact, preference, entity, rule, episodic) exposed as the memory_remember and memory_recall agent tools, with recall ranked by keyword overlap, importance and access frequency.

A headless-first macOS Computer Use driver for DeepSeek Harness with AX-first observations, window-bound multimodal evidence, host-owned approval, and evidence-backed action receipts

Skill routing for DeepSeek Harness: embeds skills and each user task with a local model, keeps the clearly-relevant skills with a gap-based selection rule, and auto-injects their full bodies into the prompt.

An Agent-safe context compressor for DeepSeek Harness. It semantically preserves critical tool outputs such as errors, file paths, JSON payloads and command results, instead of mechanically truncating the context.

Deny an AI agent access to .env files, credential stores, keys and any path you hide — across file tools, shell commands, search selectors and run_code. A DeepSeek Harness (dsh) plugin.

Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由，虚拟 smart 模型零配置接入。

在 DeepSeek Harness 对话中以会话级 artifact 安全展示交互式 HTML 可视化。

Persistent, searchable, per-project memory for the DeepSeek Harness: decisions, rules, and sprint context in a queryable DuckDB file, rules enforced on every model request, with a full management UI in the Web Client

Xiaomi MiMo-powered voice for DeepSeek Harness: browser 🎤/🧠/🔊 UI, voice_transcribe/voice_understand/voice_speak tools, configurable voice map (preset/voicedesign/voiceclone). Fork of zhuiyueya/dsh-voice (MIT), Settings pattern from Anionex/dsh-vision-toolkit (MIT).

flykit for DeepSeek Harness — status line, file explorer with editor and live watch, and Claude Code / Pi / Codex terminals in the web GUI. Fly your agents.

Verifiable authorization, execution evidence, and offline delivery verification for DeepSeek Harness

Records scoped workflow rules and correction reminders with bounded evidence, local settings, and optional Brain Hub integration.

Multi-agent frugality defense plugin: read-ledger dedup metrics, compaction-immune rules, completion gate, cheap-model review lane.