dsh的跨会话记忆管理插件，让agent记住每一个任务的内容和进度。包含命题图、三层内存漏斗、混合向量 + 词法检索（RRF）以及浏览器端审查面板。 ｜ Cross-session memory management for DSH — lets the agent remember the content and progress of every task while executing. Includes a proposition graph, three-layer memory funnel, hybrid vector + lexical retrieval (RRF), and a browser-side review panel.
Give text-only DeepSeek models on-demand vision: upload images, DeepSeek answers by calling a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).
A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.
DSH plugin bundle: live Wallpaper Engine backgrounds for the DSH web GUI - video/web wallpapers, static scene previews, rotation lists, search, resource monitor, bilingual UI
See at a glance what DeepSeek did, and when. 📅 A beautiful usage calendar for DeepSeek Harness — every project and task's execution time, 🎡 in day / 7-day / month / year views, with recurring reminders, animations, and full theme awareness.✨
DeepSeek Harness agent preset: a study-and-execution steward persona on the full Standard tool surface, shipped with a generic Markdown rule pack for plans, vocabulary, algorithms, review and archiving.
