Cache-aware API token usage bar for the DeepSeek Harness Web UI
Native, per-workspace long-term memory for DeepSeek Harness: approval-gated writes, cited provenance, FTS cross-session ...
✨ DSH 持久化 Web 插件：输入框旁一键把模糊需求改写成 AI 智能体可执行的超级提示词。复用当前所选模型，探索优先协议 + Skills 感知，彩虹跑马边框与输入锁定，重启自动加载。MIT 开源。
dsh-delegate: model-aware subagent delegation for DeepSeek Harness — per-call models, depends_on dependency gating, per-...
Optical compression memory using DeepSeek-OCR (OCR1)
Unofficial GPT-5.6-Sol workflow, recovery, verification, and budget plugin for DeepSeek Harness.
A DeepSeek Harness (DSH) dynamic plugin that adds an ✨ optimize-prompt button to the chat composer — context-aware LLM r...
100% AI-native product delivery workflow plugin for DeepSeek Harness: full product-to-release pipeline (research → PRD →...
DSH 多方群聊协作插件（圆桌）：把不同人设的 AI Agent 拉进同一研讨房间，互相讨论、交叉补充、质疑修正，最终一键总结出综合方案；也支持把工作区已有的对话框拉进来参与讨论，消除信息隔离。支持手动 @ / 全体研讨 / 接力链三种发言...
dsh-observability Two small plugins for DeepSeek Harness that close the observability gap around external subagent runs....
Async LLM context relay between DeepSeek Harness sessions and Agent Team Rooms
team-task for DeepSeek Harness (dsh): long-horizon multi-agent tasks — reviewed plan DAG, runtime-owned settlement, even...