vrr/ruvector
2
0
Fork 0
mirror of https://github.com/ruvnet/RuVector.git synced 2026-05-23 21:25:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 19
ruvector/crates/sona/wasm-example
History
Exact
rUv 5bad08c6a3 feat(sona): Add SONA self-optimizing neural architecture 
Implement complete SONA system with:
- LoRA-Ultra: Adaptive low-rank adaptation for efficient fine-tuning
- Learning Loops: Instant, background, and coordinated learning modes
- EWC++: Enhanced elastic weight consolidation for continual learning
- ReasoningBank: Trajectory storage with verdict-based learning
- WASM bindings for browser deployment
- N-API bindings for Node.js integration
- Comprehensive documentation and benchmarks

New crate: crates/sona with full implementation
Integration: examples/ruvLLM with SONA module
NPM package: npm/packages/sona for JavaScript bindings

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-03 04:36:48 +00:00
..
index.html feat(sona): Add SONA self-optimizing neural architecture 2025-12-03 04:36:48 +00:00
package.json feat(sona): Add SONA self-optimizing neural architecture 2025-12-03 04:36:48 +00:00
README.md feat(sona): Add SONA self-optimizing neural architecture 2025-12-03 04:36:48 +00:00

README.md

SONA WASM Example

Interactive browser demo of the Self-Optimizing Neural Architecture (SONA).

Quick Start

  1. Build the WASM module (if not already built):
cd ..
wasm-pack build --target web --features wasm
cp -r pkg wasm-example/
  1. Serve the example:
cd wasm-example
python3 -m http.server 8080
  1. Open in browser:
http://localhost:8080

Features

  • Real-time Learning: Record trajectories and see instant updates
  • LoRA Visualization: Watch transformation in real-time
  • Statistics Dashboard: Monitor patterns, quality, and performance
  • Interactive Controls: Adjust configuration and run experiments

Files

  • index.html - Demo page with UI
  • index.js - JavaScript logic using WASM bindings
  • package.json - NPM configuration
  • pkg/ - Generated WASM package
    • sona.js - JavaScript bindings
    • sona_bg.wasm - WebAssembly binary
    • sona.d.ts - TypeScript definitions

Usage Example

import init, { WasmSonaEngine } from './pkg/sona.js';

async function main() {
  await init();
  
  const engine = new WasmSonaEngine(256);
  const trajectoryId = engine.start_trajectory(new Float32Array(256).fill(0.1));
  engine.record_step(trajectoryId, 42, 0.8, 1000);
  engine.end_trajectory(trajectoryId, 0.85);
  
  const output = engine.apply_lora(new Float32Array(256).fill(1.0));
  console.log('Transformed output:', output);
}

main();

Performance

  • WASM file size: ~1.5MB (release build)
  • Initialization: < 100ms
  • Per-trajectory overhead: < 1ms
  • LoRA application: < 0.1ms (256-dim)

Browser Support

  • Chrome/Edge 91+
  • Firefox 89+
  • Safari 14.1+

License

MIT OR Apache-2.0