liustack/modlens
modlens is a tool for DeepSeek Harness. 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).
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
A polished, actively maintained vision plugin that gives text-only coding agents real image understanding with minimal s
README references a dedicated configuration doc, troubleshooting guide, security doc, and a health check, plus npm/Node badges implying a published, versioned TypeScript package, though no test or CI details are shown.
A dedicated docs/security.md exists and the README states it reuses existing local logins only after asking, but the install path involves npx execution and API-key handling whose specifics are not visible here.
Solves a concrete, common pain point by letting text-only DeepSeek/GLM models read pasted images and return structured OCR/layout/semantic JSON, with verified support across Claude Code, Codex, Pi, and OpenCode.
Last updated 2026-09-07, not archived, 3909 stars, and a pinned versioned release (3.26.1) indicate an actively maintained project.
README covers install commands for dsh and skills.sh, two paste workflows, provider routing, and links to configuration, troubleshooting, security, and setup guides, though the directory's install command field is 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
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 DeepSe
modlens has 4,430 stars and 136 forks on GitHub, last updated 2026-10-23.
modlens is distributed under the MIT license.
modlens 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:agent-skills、dsh-plugin。
Ephemeral-AI-Lab
Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed history, without copying the base. Agents work in parallel, commit what changed as deduplicated checkpoints, then branch, rewind or merge. Try it with LayerFS × DSH.
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)
2BingLing
DeepSeek Harness Plugin Marketplace · Continuously listing 1500+ DSH plugins: Chinese search + practical 5-dim scoring + one-click install. Web and DSH sidebar plugin forms. Plugin marketplace for DeepSeek Harness: 1500+ plugins, Chinese search, 5-dim scoring, one-click install.