Lora Learning

On-device learning with MicroLoRA adapters on @ruvector/learning-wasm (microsecond WASM adaptation), trajectories and pattern learning. Use when: ruflo should learn from verified task outcomes, adapt routing to a project, or you need to check that WASM learning is active. Skip when: one-off tasks with no feedback signal.

ruvnet Updated 104k repo stars
Ruflo animated neon sign

File contents

LoRA Learning Skill

Purpose

ruflo adapts small low-rank weights from task outcomes. @ruvector/learning-wasm (shipped with @claude-flow/cli) provides WasmMicroLoRA, WasmScopedLoRA and WasmTrajectoryBuffer. Without it the same code runs on a slower JS fallback.

When to Trigger

  • a task succeeded and its approach should be reused
  • routing keeps picking the wrong agent or model for this project

When to Skip

  • outcomes you have not verified

Commands

Check the backend

npx @claude-flow/cli neural benchmark -i 1000
npx @claude-flow/cli neural status

The MicroLoRA table appears only when the WASM module loads (measured: about 2 µs per 256-dim adaptation).

Train and reuse

npx @claude-flow/cli neural train -p coordination
npx @claude-flow/cli mcp exec -t hooks_intelligence_pattern-search -p '{"query":"auth refactor"}'

Best Practices

  1. Train only on verified outcomes (tests passed, user accepted)
  2. Keep one namespace per project
  3. If the JS fallback is reported, reinstall without --omit=optional

ruvnet/ruflo commit a4c422a304

Frequently asked questions

npx get-skill add ruvnet/lora-learning-2