276 results
Local-first vision for text-only DeepSeek Harness agents: route image understanding to a local OpenAI-compatible vision model, return structured JSON evidence (summary / OCR / layout / semantics / visual / uncertainty).
Gives a text-only LLM vision capability
DSH 静默视觉增强：主模型照常选择，图片自动交给固定视觉模型后以隐藏上下文返回主模型。
DSH plugin: vision_read — route image reading to a dedicated vision model (e.g. Kimi K3) so text-only agents can see images
Adaptive image routing for DeepSeek Harness: pass images directly to native multimodal models and transcribe them only for text-only models.
dsh-eye-vision: give text-only DeepSeek Harness models eyes — image understanding via any OpenAI-compatible multimodal API. Fork of dsh-free-vision with custom-provider fixes and an allowed-directories whitelist.
MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness
Multimodal plugin for DeepSeek Harness: understand images and generate images through configurable OpenAI-compatible or DashScope endpoints.
火山方舟 Coding Plan LLM provider for DeepSeek Harness — provider-scoped PDF、图片与 Responses API 流式支持
Model pricing and capability board for DeepSeek Harness: compare per-1M-token prices, find the cheapest route, and see coding/agentic/vision tags for every LLM you can connect — in the DSH settings UI.
Visual plan mode for DeepSeek Harness: structured plan.json + plan.md, an editable React Flow canvas, comments, plan diff, versioned revisions, and reliable write-back to the agent.
DeepSeek Harness plugin: bridge image-bearing messages to a user-configured OpenAI-compatible vision endpoint when the active text model cannot see images
辅助视觉模型：图片→文本描述，供文本模型、浏览器截图兜底与聊天贴图降级使用
Image generation for DeepSeek Harness: a generate_image tool with pluggable providers — the FAL queue API or any OpenAI-compatible images API. The picture is shown inline in the conversation; the model receives either a link (works with any chat model) or the image itself (needs dsh-vision-bridge or a vision-capable model).
Remote development for the DeepSeek Harness web GUI: connect a workspace to an SSH server, provision a .dsh-server there, run its files, terminals, conversations and agents on that machine — Work mode included, as the harness running there shown here
Agnes 全模态插件 for DeepSeek Harness：看图（agnes_vision）、生图/图生图（agnes_image）、视觉桥（带图消息可发送并自动交给 Agnes 视觉分析）。密钥经 DSH 凭据服务读取，不写入代码。
Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.
A vision bridge for text-only DeepSeek Harness models: registers an `analyze_image` tool that answers questions about images via ANY OpenAI-compatible vision/multimodal endpoint (SiliconFlow, DashScope, Zhipu, OpenRouter, Ollama, ...).
DeepSeek Harness 视觉理解插件：把用户消息与工具结果中的图片翻译成文字描述，交给纯文本任务模型（如 DeepSeek）。
文档文字识别。用户提供 PDF/扫描件/图片（合同、发票、书页、截图），需要提取文字、转成可编辑文本时使用。扫描件自动 OCR（macOS Vision，中英文）。Document OCR: extract editable text from PDFs, scans, and images (contracts, invoices, book pages, screenshots) via macOS Vision.
Edit a user message in conversation history: confirm the revision, drop everything after it, and regenerate from the revised prompt in a forked session.
明眸 VisionBridge - 自研视觉桥：瞎子模型收图时自动调用视觉模型识别，把识别文字喂回主模型，无感、可配置、升级不丢
DSH 装备升级套件：token 费用面板（dsh-cost）、会话文件预览（dsh-plugin-file-preview）、外网搜集（dsh-research-mcp，工具名 mcp__research__*）、视觉桥接（vision-bridge，给无视觉模型看图）、微信双向通道（dsh-wechat-bridge，微信发消息→本机执行→回微信）。已安装时，用户问"花了多少钱/预览这个文件/搜一下外网/看这张图"直接按对应组件办事；未安装时给出 install.sh 一键安装命令。
Route image-bearing turns to a configurable image-capable model for DeepSeek Harness