oil-oil/dsh-vision
dsh-vision is a tool for DeepSeek Harness. Near-native image understanding for DeepSeek Harness
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Well-documented, actively maintained vision bridge plugin that solves a real gap for text-only DeepSeek models with stro
README documents a CI workflow badge, pnpm install/check dev commands, and TypeScript source, indicating reasonable engineering rigor though no test suite is explicitly mentioned.
README states API keys are stored via Harness's official credential service, are write-only in the browser, never written to the repo, and vision output is marked as untrusted observation data with no system authority.
The plugin directly addresses a common pain point by letting text-only DeepSeek models handle images through a vision bridge, with native passthrough for vision-capable models and local OCR fallback.
Last updated 2026-08-18 with an active CI badge and explicit support for Harness rc.6 and rc.7, indicating current and ongoing maintenance.
README provides clear install command, a how-it-works table, UI and YAML configuration instructions, see-skill compatibility, security boundary, and development setup.
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
npx @deepseek-ai/dsh plugin --profile web add github:oil-oil/dsh-visionThis command was extracted from an explicit README install reference and is display-only; the DSH host will not execute it automatically.
PROJECT TOPICS
VALIDATION LADDER
FAQ
Near-native image understanding for DeepSeek Harness
dsh-vision has 88 stars and 8 forks on GitHub, last updated 2026-08-18.
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-understanding、multimodal、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.