Best DSH Vision & OCR Plugins

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网第一个 DeepSeek Harness 视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。

Connect a sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and global vision/image tools.

HeartFlow (心虫) AGI layer-1 discriminator gate as a DSH plugin: 47-dimension rule-based text checking (heartflow_check tool) plus automatic output supervision at tools/post-execute, fail-closed when engine missing.

Dsh-visual-plugin.Give your text-only model eyes: forward user images to any OpenAI-compatible vision model and see the results in a Web UI right panel

Free vision & image generation for DeepSeek Harness — paste an image into any chat, even text-only sessions. GLM-4V-Flash / Qwen3-VL / Gemini failover chain, ModLens-style structured evidence, Kolors generation. 免费读图·生图 · 三引擎容错 · 无 Key 入库

Cross-platform Computer Use for DeepSeek Harness: virtual-mouse human-like operation (screen_observe + computer_click + type + key + scroll + drag, 11 tools), AX-tree zero-vision-cost mode with free GLM-4V-Flash vision fallback, safety guards (snapshot TTL / app whitelist / dangerous-action approval / password-box protection).

MCP bridge to gemini.google.com: vision analysis of images and videos, Imagen image and Veo video generation, and conversation management using the logged-in browser session with no API key.

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed to text via any OpenAI-compatible VLM before reaching the text-only DeepSeek — a keyed fast path (default qwen3.7-flash; DashScope/Zhipu/OpenRouter or any OpenAI-compatible endpoint) with your own key, or local Ollama auto-detected with zero config.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

`describe_image` tool: a vision bridge that sends images to mimo-v2.5 through the opencode Zen API (credential `OPENCODE_GO_API_KEY`, free route first with paid fallback) and returns text descriptions for text-only models, with native passthrough and ImageMagick transcoding of SVG/TIFF/HEIC formats.

Bilibili video analysis: metadata, transcript (ASR fallback via Bijian/sherpa-onnx/whisper.cpp), comments, danmaku, and sharp keyframes with optional local vision descriptions.

A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.

Academic writing guard (EN/ZH bilingual rules): local-regex linter for revision-process residue, defensive writing and AI-writing tells (em-dash abuse, not-X-but-Y, LLM word spikes, rule of three); writing_audit + writing_rules with incremental auto-audit that only reports new/resolved issues on paper file writes.

Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sidecar, and leave native vision models untouched.

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

Native vision capability extension, using either Zhipu (free) or Qwen-VL (local).

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a local KoboldCpp (llama.cpp) server through koboldcpp_run and koboldcpp_vision tools, with on-demand server lifecycle management.

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

External vision plugin for DeepSeek Harness: whale-button config panel, image recognition with auto-reply, and agent screenshot/recognize tools.

dsh plugin: Chrome sidebar extension that lets DSH operate your browser directly—no vision capabilities required. dsh 插件：一款 Chrome 侧边栏扩展程序，可让 DSH 直接操控您的浏览器——无需视觉能力。

Composer-attached images are auto-described by an OpenAI-compatible vision model and handed to text-only models (DeepSeek) as text. ???????????

Local-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.

Synesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.

Agent-callable vision tool that describes local images via any OpenAI-compatible vision endpoint you configure, with an optional multi-model cross-check and no built-in keys.

Transparent image guard for text-only routes: paste images without the 400 session deadlock, plus a vision_analyze tool for OCR/PDF/docx/pptx/video.

让纯文本模型更好地做视觉任务的DeepSeek Harness插件：带意图的图片问答、长截图 OCR、UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

Vision toolkit for text-only DeepSeek: model-invokable `vision` tool, wrapper adapters for deepseek/opencode-go (v4 flash/pro), Antigravity IDE quota (default, flash/pro) / any OpenAI-compatible VLM / Gemini / local Ollama channels, evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Codex-backed `web_search`, `image_gen`, and `image_vision` tools for DeepSeek Harness, reusing ChatGPT OAuth login state.

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

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, never spawns or owns processes.

Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.