xing666173/dsh-vision-hub
dsh-vision-hub is a tool for DeepSeek Harness. DeepSeek Harness EAC vision suite: 15 pixel-level vision tools (enhanced dsh-tool-vision) + bridge inline preview + drag-and-drop file upload, single-endpoint driven, clean conversation, EAC native settings support
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Feature-rich vision toolkit for text-only DeepSeek models, but install path is unclear and security details are thin.
README documents structured subdirectories (tool-vision/, bridge-preview/, file-drop/), dependency handling, and a list of fixed upstream bugs, but no tests or CI are mentioned.
README claims path-escape blocking, network-disabled HTML screenshots, and overwrite protection, yet the config example shows a plaintext apiKey field and the license is NOASSERTION, so risk cannot be fully assessed.
Solves a concrete, common pain point by giving text-only DeepSeek models 15 pixel-level vision tools plus inline preview and drag-drop upload for non-image files.
Last updated 2026-08-21, not archived, and the README references versioned components (tool-vision 0.4.0, bridge-preview 0.1.1, file-drop 1.0.0) indicating ongoing work.
README provides quick-start steps, copy-paste agent install/config prompts, a tool table, and links to docs/ENHANCEMENTS.md, docs/INSTALL.md, and docs/examples.md, though the actual install command is listed as unknown.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryPROJECT TOPICS
VALIDATION LADDER
FAQ
DeepSeek Harness EAC vision suite: 15 pixel-level vision tools (enhanced dsh-tool-vision) + bridge inline preview + drag-and-drop file upload, single-endpoint driven, clean conversation, EAC native settings support
dsh-vision-hub has 4 stars and 0 forks on GitHub, last updated 2026-08-21.
dsh-vision-hub is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:ocr、vision。
liustack
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). | The strongest vision add-on plugin for DeepSeek Harness, adding vision capability to text-only models like DeepSeek and GLM, paste an image and get structured JSON evidence (OCR, layout, semantics).
tong-io
TongFlow — Multimodal GenAI Studio
Anionex
[dsh] A more powerful visual toolkit for text-only models: one-line install and use, paste images for direct recognition, multi-image Q&A, screenshot-to-frontend UI restoration, and more｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
DDDMUC
Free web search provider for DeepSeek Harness - DuckDuckGo backend, no API key needed
anysearch-team
AnySearch web search provider and advanced search tools for DeepSeek Harness (DSH)
omdsh-dev
Connect DSH to your database for conversational data analysis and actionable business insights.