@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.
564 results
DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.
A community plugin marketplace for DeepSeek Harness, built to the official plugin spec — browse, search and install 9000+ human-curated community plugins without leaving the app. · DeepSeek Harness 社区插件市场(遵循官方开发规范):9000+ 人工精选社区插件,每日更新。
Unofficial DeepSeek Harness LLM provider plugin for Command Code, ported from pi-commandcode-provider (MIT). Registers the 'commandcode' provider route with a Models-page card and live model catalog.
SeekTTY, a pluggable DeepSeek-colored terminal surface for DeepSeek Harness
Bloom for DSH — 玻璃+莫兰迪主题。10 套 OKLCH 配色(黛蓝/朱砂/桃夭/天青/竹青/赭石/青金/琥珀/落霞/青莲),明暗自适应;磨砂玻璃面板默认常开;微动效 + 版本/更新指示。零依赖、TypeScript、WCAG AA。
Persistent multi-model squads for DeepSeek Harness with durable orchestration, DAG workflows, run history, and provider-reported token usage
DeepSeek Harness 插件:对话内多源搜番,卡片详情、磁力复制与规则流媒体在线播放
DeepSeek Harness plugin: dispatch work to DSH agents from Claude Code / Codex, as native subagents with live progress
Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.
Hanai Worth · 值见 — a local-first A-share value research workbench powered by DeepSeek Harness
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.
Free OpenCode Zen models for DeepSeek Harness (DSH): native dsh-llm adapter plugin, no API key.
A bilingual floating pet for DeepSeek Harness with runtime status, context and lifetime token usage, trends, and optional completion sounds.
Session-aware sandbox escalation compatibility plugin for DeepSeek Harness
Primary DSH entry for using ChatGPT with local code, Agent Helm engineering capabilities, and native DSH sessions.
Accessibility-first macOS Computer Use capability for DeepSeek Harness with stale-observation protection, app leases, confirmations, screenshots, and Web diagnostics
Multi-session terminal workbench plugin for DeepSeek Harness
Steam Workshop-style plugin browser for the DeepSeek Harness (DSH) web UI: search, hot/newest/trending windows, Chinese keyword mapping, bilingual description & README translation, plugin-signature filtering, one-click install/update/uninstall, and an installed-plugins manager.
DeepSeek Harness (DSH) local-first cross-session project memory: bounded cache-friendly Hot Memory, BM25 recall/cache, provenance, lifecycle and bilingual Web GUI; no embeddings, external service or bundled runtime dependencies.
Multi-provider Web Search & Fetch for DeepSeek Harness — 8 deeply adapted providers, SearchHints, resilient fallback, and native X / Xiaohongshu retrieval
The Feishu UI for DeepSeek Harness (dsh) — a dsh-native plugin: live streaming cards, in-card questions & approvals, one-QR setup.
Local PDF, Office, image, and OCR document intelligence for DeepSeek Harness.
Solo-style isolated brainstorm branches and Handoffs for DeepSeek Harness
DeepSeek Harness dual-face plugin: Codex-style file references (@path), fully bundled document→Markdown (MarkItDown engine, 20+ formats), mature image handling (read_image for multimodal routes, automatic vision descriptions for text-only models), read_document tool.