Favio8/dsh-plugin-deepeye
dsh-plugin-deepeye is a tool for DeepSeek Harness. DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
A well-documented vision plugin for DSH with multi-backend support, but unverified install command and no visible tests
README describes a structured Cordis plugin with caching, retries, timeouts, and HMR-safe wrapping, but no test suite, CI config, or source layout is shown.
API keys are read from environment variables with documented precedence and no plaintext secrets are shown, but the plugin downloads remote images and wraps LLM model resolution, so risk cannot be fully assessed.
Solves a concrete gap by giving text-only DeepSeek models image description, OCR, VQA, layout analysis, and clipboard/paste-image translation.
Last updated 2026-08-17 with an active feature set and non-archived status, though only 4 stars and no release history are visible.
README covers installation, layered config, provider examples, full option reference, tool table, and pasteCompat internals, but the install command is listed as unknown and the excerpt is truncated.
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
DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.
dsh-plugin-deepeye has 4 stars and 1 forks on GitHub, last updated 2026-08-17.
dsh-plugin-deepeye is distributed under the MIT license.
dsh-plugin-deepeye 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:multimodal、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.