sfyyy/dsh-vision-bridge
dsh-vision-bridge is a tool for DeepSeek Harness. On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Useful on-demand vision bridge for text-only DSH sessions, but limited evidence on tests, CI, and security hardening.
README describes a clear architecture (agent/pre-step hook, deriveMessages wrapper, single provider route) but shows no test suite, CI config, or repository structure evidence.
README mentions API keys synced to the DSH credential store and an admission bypass, but no audit of the bypass or key handling is provided, so risk is unclear.
Solves a real pain point by giving text-only DeepSeek sessions on-demand image understanding while keeping vision calls cheap (image + question only).
Last updated 2026-08-16 with an active npm package and sponsor activity, but no commit history or issue data is given to confirm ongoing maintenance.
Install command, configuration JSON, settings UI path, and a how-it-works diagram are documented, though the README excerpt is truncated and lacks troubleshooting detail.
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 @dsh-extension/dsh-vision-bridgeThis 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
On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model
dsh-vision-bridge has 6 stars and 0 forks on GitHub, last updated 2026-08-16.
dsh-vision-bridge is distributed under the MIT license.
dsh-vision-bridge 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、ocr、on-demand-vision、openai、openai-compatible、vision、vision-language-model。
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.