modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
DeepSeek Harness plugin
Local-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.
Jump to installSend the GitHub link to DSH, Codex, or another agent. Ask it to explain the purpose, access, installation, and removal steps, then wait for your approval before running commands. Paste the README if it cannot open the link.
dsh plugin --profile web add github:gloryxpnv/dsh-tool-visionThis command comes from the community plugin list. Open the repository and check the setup steps and scripts before running it.
These are the original fields from the community list, kept here so you can compare them with the GitHub repository.
registry-record.jsonCheck against GitHub before use{
"name": "dsh-tool-vision",
"owner": "gloryxpnv",
"category": "tools",
"description": "Local-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.",
"install": "dsh plugin --profile web add github:gloryxpnv/dsh-tool-vision",
"npm": null,
"stars": 0,
"added": "2026-08-15",
"source": "registry"
}See which files it changes, which websites or API keys it can access, which install scripts it runs, and whether it has a license and removal steps. GitHub stars only show attention.