LoRA Learning
ruflo adapts small low-rank (LoRA) weights from task outcomes. The fast path is @ruvector/learning-wasm, which ships with @claude-flow/cli. It provides WasmMicroLoRA, WasmScopedLoRA (per-operator adapters) and WasmTrajectoryBuffer. Without it the same code runs on a slower JS fallback.
Check the backend
npx @claude-flow/cli neural benchmark -i 1000 # MicroLoRA table: average adaptation time in microseconds
npx @claude-flow/cli neural status
The benchmark's MicroLoRA table only appears when the WASM module loads. Measured: about 2 µs per 256-dim adaptation. If you see RuVector JS fallback (install @ruvector/learning-wasm ...), the optional dependency was skipped. Reinstall without --omit=optional.
Learn from work
- Record the task as a trajectory:
mcp__claude-flow__hooks_intelligence_trajectory-start, then..._trajectory-stepfor each decision, then..._trajectory-endwith the outcome. - Store a reusable pattern:
mcp__claude-flow__hooks_intelligence_pattern-store. - Train:
mcp__claude-flow__neural_train, or on the CLInpx @claude-flow/cli neural train -p coordination. - Reuse:
mcp__claude-flow__hooks_intelligence_pattern-searchbefore the next similar task.
Good practice
- Only record outcomes you have verified (tests passed, user accepted). Training on unverified successes teaches the wrong thing.
- Keep one namespace per project so adapters do not mix domains.
neural optimizequantizes stored patterns to Int8 (about 4x smaller) once the set is stable.
