dsh-splash-launcher
DSH Windows one-click launcher: opens the browser splash animation immediately, boots dsh web, and reveals the GUI when ready; also registers the desktop_launch agent tool.
754 results
DSH Windows one-click launcher: opens the browser splash animation immediately, boots dsh web, and reveals the GUI when ready; also registers the desktop_launch agent tool.
Prism: a glassmorphism theme layer for the Web surface — adjustable blur, frost, six per-zone glass opacities, damped knobs, font scale/family, accent and backdrop hue, animated aurora or photo/GIF wallpaper
Dynamic chat-image bridge, recognition tool, onboarding wizard and failure self-check for text-only models on DeepSeek Harness
DSH Pet Corner: a floating pet, keyless pet-image proxy, favorites, and plugin-owned settings API
Wallpaper plugin for the DeepSeek Harness web GUI: translucent app surfaces over a user-picked local image, GIF, or video background, plus one-click Wallpaper Engine imports
Spritely — a floating work-state mascot for the dsh web UI: it animates with the agent's live activity, tracks the cursor, and offers switchable characters, draggable placement, and customizable backgrounds.
Feishu and Lark text, image, and file channel bridge for DeepSeek Harness
In-place three-decimal cache-hit percentage plus a widened composer stats line for DSH Web.
AI audio generation plugin for the dsh web GUI: multi-vendor TTS/music/sound-effect channels (OpenAI-compatible, ElevenLabs, MiniMax, Stability AI and custom), per-channel model/voice catalogs, Agent tool and a sidebar AI 音频 panel.
Local-first file conversion for DeepSeek Harness - images, PDF, data, audio/video and office documents. No API keys, no uploads, no token cost.
DeepSeek Harness multi-model routing plugin: route tasks to custom specialist agents (vision / image generation / translation / speech / subagent) with per-agent providers & models, multimodal account sign-in, OAuth account pools, and realtime usage stats
Claude Code CLI as an LLM provider for dsh (DeepSeek Harness): live model list, per-session resume, approval relay, images, a memory/rewind/changes panel, and workspaces on remote SSH boxes
MiniMax token-plan quota dock for DSH web — drop-shape 5h usage %, click for detail panel, auto-hides for non-MiniMax models.
Export a minimal, secret-scrubbed, replayable problem bundle for DeepSeek Harness via the /repro command.
Rizen Signal Console — digital arcade HUD skin for DeepSeek Harness Web GUI: neon cyan/violet/magenta palette, pixel fonts, animated HUD sprites, custom crosshair cursor
Minimal auto chess for the dsh web GUI: AI action routes, model catalog, and default prompt (node half) plus the conversation-view tab with the boards (browser half)
DeepSeek Harness (dsh) plugin: prune the tool schema and inject a structural preamble on a session's first turn only.
External vision proxy plugin for DeepSeek Harness, enabling text-only models (DeepSeek-V3 / R1) to analyze and understand images via OpenAI-compatible vision APIs.
FileLens — right-column file explorer for DeepSeek Harness: lazy directory tree, multi-format preview (Markdown/JSON/CSV/diff/log/hex/image), search & grep, tabs, inline editing with containment + version-guarded writes.
Unit conversion toolbox for DeepSeek Harness (dsh): length, mass, temperature, area, volume (incl. cooking), speed, time, data sizes (decimal MB vs binary MiB), data transfer rates (Mbps vs MB/s), acceleration (m/s², g-force), illumination (lux, foot-candle), pressure, energy, angle, frequency, power (mechanical/metric/electric horsepower), force, torque, typography (px/pt/em/rem), fuel economy (mpg ↔ L/100km) — zero runtime dependencies
Out-of-tree Web plugin: load folder-based theme packs (tokens, CSS, fonts, images) and switch them through ThemeRuntime
Give DeepSeek Harness agents the ability to read images directly: a model-facing read_image tool that answers questions about an image through any OpenAI-compatible vision endpoint.
Let the model render an image into the DSH web chat flow (QQ/WeChat style) via a show_image tool: the message content keeps only the path text, the image never enters model context, and the browser shows the picture inline, scrollable with history.
Registers generate_image and generate_video tools for Agnes AI media models (agnes-image-2.5-flash, agnes-video-2.5-flash) in DeepSeek Harness. Supports multi-image reference via reference_image_urls.