Sovereign Swarm Coherence Transformer v1 (ALPHA WebAssembly Edition)

Zero-Latency Client-Side Inference for Browser (React/Next.js) & Mobile (React Native/iOS/Android) Published by ItsNotAI LABS (Dallas, Texas)

The Sovereign-Swarm-Coherence-v1-alpha repository contains the lightweight ONNX & WebAssembly (WASM) client-side package for running inference directly inside web browsers and mobile apps with 0ms server latency and zero cloud API infrastructure costs.

⚡ WebAssembly (WASM) SDK Features

Direct In-Browser Inference: Compiles PyTorch weights into ONNX Runtime WASM (model.onnx).
Zero Server Latency: Executes directly on client CPU threads using SIMD & multi-threading.
Full TypeScript SDK Included: Includes @sovereign-engine/wasm-sdk source and pre-built bundles.
100% Offline Capable: Zero network dependencies after initial WASM module download.

🚀 Quick Start (React / Next.js)

import { SovereignSwarmCoherenceWasm } from '@sovereign-engine/wasm-sdk';

const swarmEngine = new SovereignSwarmCoherenceWasm(
  'https://huggingface.co/ItsnotAilabs/Sovereign-Swarm-Coherence-v1-alpha/resolve/main/model.onnx'
);
await swarmEngine.init();

const syncResult = swarmEngine.calculateSwarmSync(
  [0.12, 0.15, 0.11, 0.14, 0.85],
  [[1.2, 3.4], [1.3, 3.5], [5.0, 8.0]]
);
console.log('Kuramoto R:', syncResult.kuramoto_order_parameter_R);

🔬 Model Parameter Integrity

Trainable Parameters: 800,019
Positional Encoding Buffer: 640,000
ONNX Model Size: 5.51 MB
WASM Inference Latency: 1.876 ms

📄 License

Apache 2.0 License © ItsNotAI LABS

Downloads last month: 23

Safetensors

Model size

1.44M params

Tensor type

F32