{
  "@context": "https://schema.org",
  "@type": "SoftwareApplication",
  "@id": "https://www.insightits.com/products/chorus-fabric.html",
  "slug": "chorus-fabric",
  "canonicalName": "CHORUS Fabric",
  "name": "CHORUS Fabric — Tensor-Native Agent Protocol",
  "canonicalUrl": "https://www.insightits.com/products/chorus-fabric.html",
  "knowledgeUrl": "https://www.insightits.com/catalog/chorus-fabric.json",
  "markdownUrl": "https://www.insightits.com/catalog/chorus-fabric.md",
  "family": "supporting",
  "infraFamily": null,
  "recordType": "product",
  "status": "published",
  "parentProduct": null,
  "whatItIs": "Patent-pending tensor-native agent protocol that streams float32 embeddings directly over gRPC — no text, no tokens, no JSON.",
  "problem": "Agent-to-agent HTTP/JSON burns bandwidth and re-serializes embeddings that already exist as tensors.",
  "isNot": [
    "ChorusControl (ops plane)",
    "ChorusMesh (PrismLib cluster)",
    "A text-prompt protocol — not for short prompts without tensor transport"
  ],
  "alternatives": [
    {
      "name": "HTTP/REST JSON embedding payloads",
      "relationship": "Published product claim is 4.45× less bandwidth vs HTTP/REST for 128-dim float32 (548-byte gRPC vs 2,440-byte HTTP). Not a named-vendor bake-off page."
    }
  ],
  "features": [
    {
      "name": "4.45× Less Bandwidth",
      "description": "548-byte gRPC streams vs 2,440-byte HTTP/REST for 128-dim float32 — no serialization round-trip."
    },
    {
      "name": "0 ms Cipher Overhead",
      "description": "Tensor multiplication cipher runs on the same GPU as inference — transatlantic p50 matches physical minimum."
    },
    {
      "name": "Neural Watermark Auth",
      "description": "SHA-256 seeded unit vector in every message — 7,766 / 7,766 verified transmissions, tamper-evident at the math layer."
    }
  ],
  "architecture": "Modes: Direct; Orthogonal Isolation (Mode A); Holographic Superposition (Mode B). Neural watermark: SHA-256 seeded unit vector. Requires Python ≥3.10, PyTorch ≥2.0, gRPC ≥1.64.",
  "useCases": [
    "LangGraph, AutoGen, and CrewAI pipelines that already hold embeddings",
    "Multi-agent hops where JSON serialization is the tax"
  ],
  "benchmarks": {
    "published": true,
    "summary": "Published product measurements: 4.45× less bandwidth than HTTP/REST for 128-dim float32 (548-byte gRPC vs 2,440-byte HTTP); 0 ms cipher overhead; neural watermark 7,766 / 7,766 verified transmissions.",
    "disclosures": [
      "Vendor-authored product measurements, not a named-vendor bake-off page."
    ],
    "urls": [
      "https://www.insightits.com/whitepapers/chorus-fabric.html"
    ]
  },
  "github": "https://github.com/insightitsGit/chorus-fabric",
  "pypi": "https://pypi.org/project/chorus-fabric/0.1.0/",
  "documentation": [
    {
      "title": "Whitepaper",
      "url": "https://www.insightits.com/whitepapers/chorus-fabric.html"
    },
    {
      "title": "Whitepaper PDF",
      "url": "https://www.insightits.com/docs/chorus-fabric-whitepaper.pdf"
    },
    {
      "title": "issues",
      "url": "https://github.com/insightitsGit/chorus-fabric/issues"
    }
  ],
  "install": "pip install chorus-fabric. MIT license. 4.45× less bandwidth than HTTP/REST.",
  "version": null,
  "relatedProducts": [
    "prismlib",
    "prismcortex"
  ],
  "publisher": {
    "@type": "Organization",
    "name": "Insight IT Solutions",
    "legalName": "Insight IT Solutions LLC",
    "url": "https://www.insightits.com"
  }
}