linenxi-ctrl/dsh-vision
dsh-vision is a tool for DeepSeek Harness. Adds external image recognition models to DeepSeek Harness: round whale button, send image for recognition with auto-return, model autonomous screenshot + image recognition tools, automatic multi-protocol adaptation, one-click install for beginners (auto-download if Node.js is not installed)
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Useful vision bridge for text-only DeepSeek Harness models, but review the auto-download installer and plaintext API key
README documents a clean modular layout (host/client/tool split, cordis.patch.yml, install.mjs) but no tests, CI, or linting are mentioned anywhere.
The installer auto-downloads a portable Node.js from third-party mirrors (npmmirror/Huawei/Tencent) and executes it, and the API key is stored in settings.yaml as a plaintext secret, though the key is described as non-echoed in the UI.
It solves a real gap by giving non-vision DeepSeek Harness models image recognition via an external vision API, with screenshot tooling and auto-return of recognized text into the conversation.
Last updated 2026-08-15 with version v0.2.6, an active npm package, and documented update/uninstall paths, indicating ongoing maintenance.
The README covers install (npm and offline), configuration fields, protocol adaptation tables, custom templates, and uninstall steps, though the excerpt is truncated mid-sentence in the custom responsePath section.
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 repositoryINSTALL REFERENCE
dsh plugin --profile web add @linenxi-ctrl/dsh-visionThis command passed the install-plan safety checks and can be executed by the DSH host. Validation is not a security audit or official endorsement.
PROJECT TOPICS
VALIDATION LADDER
FAQ
Adds external image recognition models to DeepSeek Harness: round whale button, send image for recognition with auto-return, model autonomous screenshot + image recognition tools, automatic multi-protocol adaptation, one
dsh-vision has 12 stars and 0 forks on GitHub, last updated 2026-08-15.
dsh-vision is distributed under the MIT license.
dsh-vision 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:image-recognition、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.