@anionex/dsh-vision-toolkit
DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.
273 results
DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.
Persistent multi-model squads for DeepSeek Harness with durable orchestration, DAG workflows, run history, and provider-reported token usage
Agent-first task board for the DSH web GUI: host-authoritative task ledger with taskboard_* agent tools, project (= workspace) claim boundaries, per-task model execution in fresh sessions, optional per-task git-worktree isolation (dedicated task branches,
DSH Web selection-annotation plugin: select assistant text, annotate (optional), and press Enter to send the annotation block with your message — the model replies to each annotation by number, with hoverable chips in the reply.
Google Antigravity (agy CLI) models for DeepSeek Harness — stream Gemini/Claude/GPT-OSS subscriptions into DSH with thinking, tool activity, token usage and in-GUI Google OAuth login.
AI image generation plugin for the dsh web GUI: text-to-image and image-to-image through configurable provider channels (gpt-image-2 / grok-imagine-image / nanobanana series / seedream-5.0-pro / dall-e-3, with native xAI Grok Imagine, Google Nano Banana and ByteDance Seedream request shaping), per-channel model catalogs, a three-column studio beside the native conversation, an infinite canvas with node-graph workflows (annotation boxes with attached prompt cards, local background removal, AI layer split, per-node model choice, file nodes with any-file upload, and a canvas skill system covering skill-driven next steps on every node: text polish, image description, content extraction, and long-running headless-agent pipelines such as image-to-editable-ppt, with a local skill library that installs and removes skills from URLs or uploaded archives), an ecommerce product-set mode and a prompt template library.
DSH plugin exposing MinerU document parsing tools to the model, with a web UI settings page for the API base URL.
客制化DSH(Custom DSH): web-surface theming (wallpaper, frosted glass, accent, translucent surfaces), configurable keyboard shortcuts (new conversation / model / thinking effort / composer gestures / usage panel), an app-usage panel, and entrance motion for conversations, the sidebar, and new conversations. Zero shell edits.
Context-window metadata catalog and settings UI for configured DeepSeek Harness model routes.
DeepSeek Harness CLI core bundle: interactive coding terminal, durable sessions, and model management for dsh --profile cli
Gomoku (five-in-a-row) for the dsh web GUI: AI move routes, model catalog, and default prompt (node half) plus the conversation-view tab with the board (browser half)
UltraMath 数学建模竞赛多 Agent 求解插件(registry 元数据 + bundle 机制):把 UltraMath 主控 + 4 角色预设幂等同步到 ~/.dsh/.agent-presets/,并把 SKILL.md、33 篇模型库技能、论文模板(templates/)与审稿脚本(scripts/)同步到 ~/.dsh/skills/ultramath/。纯 node 半侧,无浏览器 UI,不改 DSH 核心源码。
DSH custom tools: manage user-defined JavaScript tools in the settings UI with a Monaco editor; the model creates its own tools through custom_tool_create
MuseAI tavern for the dsh web GUI: a MuseAI conversation-view tab (right of Trajectory) with background / chat / adventure / bond / settings pages ported from MuseAI, running entirely on models configured in DeepSeek Harness (no separate API config)
Floating macOS-glass DeepSeek usage panel for the DSH web UI: live official balance + token usage (today, session, 24 h smooth trend, per model) without opening platform.deepseek.com/usage. · DSH 毛玻璃用量面板:官方余额 + Token 用量
DSH-standard MCP manager plugin: Settings UI + HTTP API + model-facing mcp_manager_* tools. Install with one command: dsh plugin --profile web add @xxxyz/dsh-mcp-manager@latest
Subagent Director: choose an LLM provider/model for each subagent (call args > role binding > plugin default > inherit parent) and plan main-agent/subagent responsibilities with role templates, plus a settings UI.
会话额度监控(官方 dsh bundle):按 (provider, model) 价目表记账、额度耗尽拦截 + 输入框上方进度条 UI
Visualizer plugin for DeepSeek Harness: the `visualizer` tool streams a self-contained HTML document into the chat as it is written, live-previewed by a sandboxed inline frame. One package ships both halves: the model-facing tool and the Web GUI preview card.
DeepSeek Harness plugin: configurable vision model with vision_read_image tool, composer-bar vision-model selector, and automatic image-to-text conversion for text-only main models.
DSH plugin: loopback WebSocket bridge that mirrors application frontend tools onto the agent's tool registry and forwards model calls back to the application — one bridge, many apps, key-based namespace isolation
Drop or paste images, PDFs, office docs, zips, videos and audio into the DSH composer as workspace file paths instead of model attachments — lets a text-only model agent read them via vision tools.
Windows-first bash tools for DeepSeek Harness: git_bash (Git Bash) and wsl_bash (WSL2) model tools with bwrap sandbox, approval mode, terminal-style UI cards, and background-job support
DSH Web GUI right sidebar, replaced end to end: VS Code-style file explorer plus full source control (git status, stage/unstage/discard, commit, diff, commit graph, fetch/pull/push sync, branch/remote management, git init, multi-repo switch, color-coded status, file-type icons). Every file opened from the chat, the sidebar or source control is taken over into a multi-tab editor view (Markdown/HTML/PDF/image previews, 15-language syntax highlighting, hunk-level diff editing, Ctrl+S save), with file operations (new/move/copy/delete, reveal in file explorer), a collapsible icon rail, a multi-tab bottom terminal (ConPTY) and AI commit messages from a host-configured model.