276 results
Connect your 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, global vision/image tools, and a settings page.
mm-vision (通感编码器) for DeepSeek Harness — give any text-only LLM the ability to see images via structured spatial text encoding. Registers the mm_vision tool.
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).
Adaptive image routing for DeepSeek Harness: pass images directly to native multimodal models and transcribe them only for text-only models.
Let your AI agent see and operate a real Android phone — vision + UI-tree fusion over adb, for any MCP client
Local multi-plan bridge for DeepSeek Harness: use your existing ChatGPT Codex, Claude, ZCode (GLM) and Qwen subscriptions through one loopback proxy, with a settings-page status card and one-click provisioning. No dsh core changes.
Model-facing generate_image tool for DeepSeek Harness (dsh): generates brand-new images with the Google Gemini image-generation service via the Antigravity CLI, saves them, and returns the paths. Hot-pluggable — install with `dsh plugin --profile web add dsh-tool-generate-image`.
GLM 视觉模型插件：注册 glm-vision 供应商路由（glm-4.6v 系列，image+text 输入声明）并提供 glm_vision 工具，让 DeepSeek 等文本主模型直接调用智谱视觉模型看图。
Adds opt-in image-capable sibling routes for text-only providers and converts image blocks into budgeted, locally enhanced OCR, color-statistics, pixel-scan, and metadata evidence before delegation.
Open Eyes for DeepSeek Harness: delegate images to a configurable multimodal model through OpenAI Responses, Chat Completions, or Anthropic Messages.
Eyes for text-only DeepSeek: view_image tool (any OpenAI-compatible VLM, local Ollama or cloud) + chat image-attachment bridge that rewrites pasted/dropped images into view_image path markers
Vision sidecar for text-only coding agents.
Plug-and-play image reading for text-only models: admits pasted images, projects them as [Image #N], and provides a first-class read_image tool backed by a configurable vision model, with a 读图 settings page (设置 → 读图) bridged over typert Remote.
ClawShell vision re-implemented as DeepSeek Harness plugins: self-perception (sense), self-adaptation (adapt), swarm trust + ecological niche (swarm), plus tools.
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
Multi-engine reverse image search aggregator for DeepSeek Harness. Turn one public image URL into Google Lens / Baidu / Yandex / TinEye / SauceNAO / IQDB / Ascii2d search links.
为 DeepSeek Harness 提供外部视觉模型能力：纯文本主模型通过 describe_image 工具调用外部视觉模型看图，拿到纯文字描述（多模态补全）。静态 Cordis 插件，随 DSH 启动自动加载。
让 DSH 直接操控你的浏览器，无需视觉能力：零 spawn 连接你已开启调试端口的 Chrome/Edge，截图、像素断言、执行页面 JS。Drive your already-running Chrome/Edge over CDP — screenshots, pixel assertions, page JS — no vision model, no per-use approval, zero child processes.
DSH 视觉原语工具：参考 DeepSeek《Thinking with Visual Primitives》论文，将图片路由到外部视觉模型并返回带视觉基元的文本分析。纯文本循环，对话模型无需原生视觉能力即可'看见'图片。
DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.
Vision-only desktop automation plugin for DeepSeek Harness (fusion refactor)
Browser automation toolset for dsh-tui agents: Playwright-driven browser control with deepseek-v4-flash-vision-exp visual understanding.
AI 生图 (image generation) plugin for the dsh web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint, with multi-provider support, model discovery, and agent tool registration. 与 @xiaoyuink/dsh-image-vision 同系列的图像插件。
Multi-provider media generation, visual understanding, prompt optimization, and an integrated Iris workbench for DeepSeek Harness.