MC5lan/dsh-multimodal
dsh-multimodal is a tool for DeepSeek Harness. Give DeepSeek a pair of eyes and a paintbrush: paste screenshots/images straight into the conversation, the GLM vision model first transcribes the image content precisely (error messages, code, UI preserved verbatim), then DeepSeek continues with your question —— all in the same turn, seamless throughout; when an illustration is needed, DeepSeek automatically calls the text-to-image backend and shows the image in the conversation.
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
A well-documented, security-conscious multimodal plugin that adds vision and image generation to DeepSeek Harness with n
README documents prebuilt lib/ artifacts, a Development section, CHANGELOG, and TypeScript source, but no test or CI details are visible.
README lists concrete hardening measures (API key allow-list, trusted base URLs, SSRF guard, redaction, audit log, LRU bounds) since 0.2.1.
Solves the common pain of pasting screenshots into a text-only model by transcribing via a user-configured vision provider and continuing in the same turn.
Last updated 2026-08-16, not archived, and README references versioned features up to 0.7+, indicating ongoing releases.
README covers features, security, installation commands, prerequisites, and configuration UI, though the exact install command is listed as unknown in the metadata.
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
Give DeepSeek a pair of eyes and a paintbrush: paste screenshots/images straight into the conversation, the GLM vision model first transcribes the image content precisely (error messages, code, UI preserved verbatim), th
dsh-multimodal has 4 stars and 0 forks on GitHub, last updated 2026-08-16.
dsh-multimodal is distributed under the MIT license.
dsh-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: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.