DeepSeek Harness all-in-one: no model switching — regular DeepSeek auto-routes to vision & image gen. Multi-backend: Gemini + any OpenAI-compatible (GPT-4o, Qwen-VL, GLM-4V, gpt-image, DALL-E, Flux, OpenRouter). gemini_vision/gemini_generate_image/gemini_optimize_image with vision self-check. Better than modlens.
Ambient soundtrack for DeepSeek Harness, driven by agent state. Streams 100k+ cleared tracks from AudioLib.ai — a track always finishes, so a state change never cuts one off.
DSH Web UI 增强插件:思维链默认展开、官方 API 会话价格统计、文件用系统程序打开、跑完提醒 | DSH (DeepSeek Harness) Web UI plugin: thinking-chain default-expand, session cost meter, open files in the desktop app & a completion alert
Right-side file panel for DeepSeek Harness — auto-popup when the agent creates or downloads files, with image/text preview, reveal-in-folder and open actions. Bilingual · MIT
Local personality, memory and distillation layer for DeepSeek Harness — SOUL/IDENTITY/USER/STATE persona files, cross-session memory and LLM distillation, auto-loaded on startup.