by kaixinbaba

Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.

by loyalchiiina

DSH Conversation Voice/Sound Effect Broadcast Plugin: Automatically reminds at the end of each turn, plays a failure prompt on errors; comes with 20 built-in sound effects (10 reminders + 10 nature sounds), ready to use out of the box with zero configuration, or you can clone your own voice using Volcano's "Voice Clone" feature.

by Harvey-Will

DeepSeek Harness vision plugin: 8 analysis modes (describe, OCR, chart data, UI review, object detection, compare, code-gen, debug), any OpenAI- or Anthropic-compatible vision API, with a built-in fre

by 1HelloMan1

Routes chat images to a fixed OpenAI-compatible vision model, returns factual observations to the selected main model, and reuses session-scoped observations across replay, compaction, and restarts.

by ruby1304

Vision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editi

by webkubor

DeepSeek Harness Asset Browser Plugin: View MUSE AV assets and image generation records by workspace, and copy asset direct links. DSH asset browser for MUSE AV workspaces, image libraries and generation history.

by kanchengw

Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, GUI automation, through layered evidence memory and cache.

by Ck-epsilon

Free vision OCR with adaptive tile recognition for long documents and Markdown/Word/PNG/Excel export.

by Jstn-1g

Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic s

by WYR-233

Multi-provider TTS (read replies aloud) plugin for DeepSeek Harness - pick your own provider and voice

by jypjypjypjyp

Music composition for DeepSeek Harness: the model writes a score against a bundled composing skill, and a play_score tool renders it as an inline card with a piano roll, Web Audio playback and WAV/JSON export.

by FYZB2020

Adds two Volcengine Doubao cloud speech recognizers to the DeepSeek Harness voice-input picker, optionally rewriting the transcript with an LLM.

by NagasakiSoyo-ui

Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description.

by Daive1119

Offline local OCR skill for DSH/agents - Windows native engine first, zero cloud cost

by ntesicn

Full-screen screenshot panel for DSH: marquee select, annotate, insert/copy/save, with offline OCR and translation.

by Leeminjing

On-demand vision for text-only DeepSeek models: upload images, and the model calls a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).

by MicroHEROX

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a locally running Unsloth Desktop (Unsloth Studio) server through unsloth_run and unsloth_vision tools; pure HTTP client, ne

DeepSeek Harness Image Generation Plugin: sidebar drawing page and gallery, generate and edit images within conversations, with customizable provider endpoints and proxies.

by niuniuaba

Lets a text-only DeepSeek agent read images in the same session by delegating to a vision-capable subagent, with send-time image-to-path conversion.

by Harzva

Bridge Apple on-device Vision framework (macOS) into DeepSeek Harness: OCR, image classification, face detection, document layout as local dsh tools. No network, no API key.

by davidekingsss

Agent screen capture on macOS and Windows: one tool captures the screen and returns the image itself, so the model sees it without a second call. On Windows a whole burst runs in one engine call; on m

Requires macOS and AirPods with head tracking. Answer DSH permission prompts and questions with AirPods head gestures — nod to allow or confirm, shake to reject or shift the selected option — and inst

Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool drives the local deepseek-vision-cli browser automation (manual login helper, deep-think enabled, auto-closes