# CHORUS Fabric One canonical identity. Human page: https://www.insightits.com/products/chorus-fabric.html | Field | Value | |-------|-------| | Slug | `chorus-fabric` | | Status | published | | Family | supporting | | Infra category | — | | Record type | product | | Parent | — | | JSON | https://www.insightits.com/catalog/chorus-fabric.json | | Markdown | https://www.insightits.com/catalog/chorus-fabric.md | | GitHub | https://github.com/insightitsGit/chorus-fabric | | PyPI | https://pypi.org/project/chorus-fabric/0.1.0/ | | Install | `pip install chorus-fabric. MIT license. 4.45× less bandwidth than HTTP/REST.` | | Version | — | ## What it is 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. ## Alternatives - **HTTP/REST JSON embedding payloads** — 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 - **4.45× Less Bandwidth** — 548-byte gRPC streams vs 2,440-byte HTTP/REST for 128-dim float32 — no serialization round-trip. - **0 ms Cipher Overhead** — Tensor multiplication cipher runs on the same GPU as inference — transatlantic p50 matches physical minimum. - **Neural Watermark Auth** — 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. ## Use cases - LangGraph, AutoGen, and CrewAI pipelines that already hold embeddings - Multi-agent hops where JSON serialization is the tax ## Benchmarks 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. ### Evidence 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 - [Whitepaper](https://www.insightits.com/whitepapers/chorus-fabric.html) - [Whitepaper PDF](https://www.insightits.com/docs/chorus-fabric-whitepaper.pdf) - [issues](https://github.com/insightitsGit/chorus-fabric/issues) ## Is not - ChorusControl (ops plane) - ChorusMesh (PrismLib cluster) - A text-prompt protocol — not for short prompts without tensor transport ## Related products - [prismlib](./prismlib.md) - [prismcortex](./prismcortex.md)