ruvnet/ruflo - Page 3

research-synthesize

Synthesize research findings from memory into structured reports with evidence grading, contradiction resolution, and actionable recommendations

Langue du texte source : anglais

intelligence-route

Route tasks via the 3-tier model selector and learned patterns; emits a routing rationale via hooks_explain

Langue du texte source : anglais

intelligence-transfer

Publish or fetch learned patterns across projects via IPFS (Pinata) -- the cross-project pattern transfer that hooks_transfer enables

Langue du texte source : anglais

neural-train

Train SONA + MicroLoRA neural patterns from successful task completions; runs the DISTILL + CONSOLIDATE phases of the 4-step pipeline

Langue du texte source : anglais

iot-anomalies

Detect and classify telemetry anomalies on Cognitum Seed devices. Use when investigating a device that's reporting odd metrics, before approving a firmware canary advancement, or when triaging fleet-wide health alerts.

Langue du texte source : anglais

iot-firmware

Orchestrate firmware rollouts with canary deployment and anomaly-gated advancement

Langue du texte source : anglais

iot-fleet

Create and manage Cognitum Seed device fleets with firmware policies

Langue du texte source : anglais

iot-register

Register a Cognitum Seed device by endpoint and establish agent bridge

Langue du texte source : anglais

iot-witness-verify

Verify witness chain integrity and detect provenance gaps

Langue du texte source : anglais

diff-analyze

Analyze git diffs for risk scoring, reviewer recommendations, and change classification. Use when preparing a PR, reviewing a large or cross-module change, or before merging to assess risk and pick reviewers.

Langue du texte source : anglais

git-workflow

Advanced git workflows with branch management, conflict resolution, and PR lifecycle

Langue du texte source : anglais

kg-extract

Extract entities and relations from source files to build a knowledge graph

Langue du texte source : anglais

kg-traverse

Pathfinder traversal of the knowledge graph starting from a seed entity

Langue du texte source : anglais

cron-schedule

Schedule persistent background workers via CronCreate

Langue du texte source : anglais

loop-worker

Run Ruflo background workers using Claude Code native /loop scheduling

Langue du texte source : anglais

market-ingest

Ingest and normalize market data into OHLCV vectors with HNSW indexing

Langue du texte source : anglais

market-pattern

Detect and classify candlestick patterns from ingested OHLCV data

Langue du texte source : anglais

harness-similarity

ADR-152 — weighted similarity between two harness fingerprints (genome + score JSON). Returns overall score in [0,1] plus per-component breakdown (cosine over 9 numerics, categorical agreement over 4 enums, jaccard over agent_topology). Unblocks ADR-151 §3.2…

Langue du texte source : anglais

migrate-create

Create a new sequentially numbered database migration with up/down SQL files

Langue du texte source : anglais

migrate-validate

Validate pending migrations for foreign key consistency, rollback safety, and best practices

Langue du texte source : anglais

trader-backtest

Run a historical backtest using npx neural-trader with Rust/NAPI engine (8-19x faster) and walk-forward validation; Ed25519-sign the result for paper→live tamper evidence (ADR-126 Phase 4)

Langue du texte source : anglais

trader-cloud-backtest

Run a heavy neural-trader job (long walk-forward, big Monte-Carlo, parameter sweep, model training) on the Anthropic Managed Agent cloud runtime instead of locally

Langue du texte source : anglais

trader-explain

Regulator-grade feature attribution for any LSTM/Transformer signal — single-entry PageRank ranks the top-K features that drove the prediction (ADR-126 Phase 6, ADR-123 single-entry PR)

Langue du texte source : anglais

trader-portfolio-cg

Mean-variance portfolio optimization via Conjugate Gradient — 40-60× faster than the legacy Neumann path (ADR-126 Phase 3, ADR-123 Wedge 8)

Langue du texte source : anglais

trader-portfolio

Optimize portfolio allocation using npx neural-trader mean-variance engine with risk constraints and rebalancing plan

Langue du texte source : anglais

trader-regime

Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy. Use when the user asks about market conditions, wants to pick a strategy for current conditions, or before running a backtest/signal…

Langue du texte source : anglais

trader-risk

Assess portfolio risk using npx neural-trader — VaR, CVaR, Sharpe, position sizing, circuit breaker status

Langue du texte source : anglais

trader-signal

Generate trading signals using npx neural-trader anomaly detection engine with Z-score scoring and neural prediction

Langue du texte source : anglais

trader-train

Train neural models (LSTM, Transformer, N-BEATS) on market data using npx neural-trader with confidence intervals

Langue du texte source : anglais

observe-metrics

Aggregate and display system metrics with anomaly detection for a time period

Langue du texte source : anglais

observe-trace

Trace agent execution by collecting spans and building a trace tree for a task

Langue du texte source : anglais

create-plugin

Scaffold a new Claude Code plugin with proper directory structure, plugin.json, skills, commands, and agents

Langue du texte source : anglais

validate-plugin

Validate a Claude Code plugin structure, frontmatter, and MCP tool references

Langue du texte source : anglais

memory-bridge

Bridge Claude Code auto-memory into AgentDB with ONNX embeddings, deduplicate, and enable unified cross-project search

Langue du texte source : anglais

memory-search

SOTA semantic search — hybrid (sparse+dense), Graph RAG multi-hop, MMR diversity reranking, recency weighting

Langue du texte source : anglais

vector-cluster

Cluster code by graph community detection via npx ruvector@0.2.25 hooks graph-cluster (spectral / Louvain)

Langue du texte source : anglais

vector-embed

Generate embeddings via npx ruvector@0.2.25 embed text (ONNX all-MiniLM-L6-v2, 384-dim), normalize, and store in HNSW index

Langue du texte source : anglais

vector-hyperbolic

Embed hierarchical data via npx ruvector@0.2.25 embed text and project into the Poincare ball in user code (no --model poincare flag in 0.2.25)

Langue du texte source : anglais

chat-format

Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval

Langue du texte source : anglais

llm-config

Configure RuVLLM local inference with model selection, MicroLoRA fine-tuning, and SONA adaptation

Langue du texte source : anglais