{
  "aliases": [],
  "authors": [],
  "details": {},
  "environments": [
    "cross-platform"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:36:04Z",
      "role": "primary",
      "sha256": "f4ebaafcc0ab0b9e9cc55cb587678e5c83a5bbd64469fb2cc52bc63843c5cc6d",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations"
      ],
      "url": "https://raw.githubusercontent.com/microsoft/OmniParser/HEAD/README.md"
    }
  ],
  "id": "github:microsoft/omniparser",
  "identifiers": {},
  "kind": "tool",
  "last_verified_at": "2026-10-16T06:36:04Z",
  "licenses": {
    "code": null,
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/microsoft/OmniParser"
    }
  ],
  "name": "OmniParser",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/microsoft/OmniParser/HEAD/README.md",
      "target_id": "arxiv:2408.00203",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Screenshot parser that detects interactable regions and captions icons so vision-language models can ground actions, released as V1.5 and V2 weights alongside OmniTool for driving a Windows 11 VM.",
  "topics": [
    "screen-understanding",
    "grounding"
  ],
  "updated_at": null,
  "url": "https://github.com/microsoft/OmniParser"
}