shinjiyu/dsh-plugin-multimodal
dsh-plugin-multimodal is a tool for DeepSeek Harness. Vision sidecar for DeepSeek Harness: accept pasted images on text-only models.
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Useful vision sidecar that lets pasted images work on text-only DeepSeek models, but lacks visible tests or CI.
README shows a clear TypeScript plugin structure with config schema and install steps, but no tests, CI, or build details are visible, so a neutral score is given.
README explicitly warns against committing keys and uses environment variables for secrets, but the plugin forwards images to a user-configured third-party vision endpoint, so risk depends on that endpoint.
It directly addresses a concrete, documented pain point (pasted images rejected with 'current model does not support images' on official text-only DeepSeek) and links to the relevant Discussions thread.
Last updated 2026-08-16, not archived, and the README references an active community group and promo docs, indicating ongoing maintenance.
README covers install, environment variables, YAML config, a 30-second acceptance test, and explicit anti-patterns, though it is written in Chinese and assumes DSH familiarity.
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 github:shinjiyu/dsh-plugin-multimodalThis 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
Vision sidecar for DeepSeek Harness: accept pasted images on text-only models.
dsh-plugin-multimodal has 4 stars and 0 forks on GitHub, last updated 2026-08-16.
dsh-plugin-multimodal is distributed under the MIT license.
dsh-plugin-multimodal 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: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.