ruflo

⚡ Optimization

/docs/getting-into-the-flow/optimization

Skip expensive LLM calls for simple tasks using WebAssembly transforms, and compress tokens to reduce API costs by 30-50%.

LayerComponentsWhat It Does
Agent BoosterWASM, AST analysisSkips LLM for simple edits (<1ms)
Token OptimizerCompression, CachingReduces token usage 30-50%