gugu123a/dsh-tool-see-image
dsh-tool-see-image is a tool for DeepSeek Harness. see_image tool for DSH: lets text-only models 'see' images by routing them to a configurable vision model (default Zhipu GLM-4V-Flash, free)
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Solid, well-documented plugin that gives text-only DSH models vision via a free configurable vision API.
README documents a CI badge, a regression test section, sandbox-aware ctx.fs usage, and DSH-specific schema conventions, indicating real engineering rigor.
API keys are read from environment variables (apiKeyEnv) rather than stored in plaintext, and file access goes through the sandboxed ctx.fs, though the bonus paste-to-text patch script is not detailed enough to fully assess.
Solves a genuine, common limitation: text-only DSH models cannot see images, and this routes them to a free default vision model with configurable alternatives.
Last updated 2026-08-20, not archived, and includes a CI workflow badge, suggesting ongoing active maintenance.
README covers install steps, a full configuration table with defaults, uninstall/rollback, implementation notes, and a usage example, though the install command is listed as unknown.
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
see_image tool for DSH: lets text-only models 'see' images by routing them to a configurable vision model (default Zhipu GLM-4V-Flash, free)
dsh-tool-see-image has 4 stars and 0 forks on GitHub, last updated 2026-08-20.
dsh-tool-see-image is distributed under the MIT license.
dsh-tool-see-image 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-recognition、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.