Learn from outcomes with AgentDB — store reflexion episodes with a self-critique, turn what worked into skills, report pattern and skill outcomes for reward-aware recall, record…
Set up and diagnose the agentdb plugin and its MCP server — which profile and database are in use, whether the server is connected, what it holds, and why a tool is missing or…
Store and recall memory with AgentDB's own MCP server — semantic facts (agentdb_insert/agentdb_search), reasoning patterns (agentdb_pattern_store/agentdb_pattern_search) and…
Personalized PageRank, local forward/backward push and sparse diagonally dominant solves with the zero-dependency @ruvnet/sublinear-core.
Reasoning-mode completion against DeepSeek's `deepseek-reasoner` model (R1) via /v1/chat/completions.
Create a new Architecture Decision Record with sequential numbering and AgentDB registration
Burn-rate trend over time with optional drift-alert exit code. Bins session spend into buckets, surfaces window-over-window delta, and can exit 1 when latest bucket exceeds prior…
Side-by-side comparison of ruflo vs HAL vs other GAIA harnesses — capability gaps, design decisions, and improvement roadmap
Multi-baseline counterfactual cost analysis. Compares actual session spend to hypothetical always-haiku / always-sonnet / always-opus routing baselines.
Diagnose Ruflo health, then report system, MCP server, and active-agent status without changing the installation
Cost per million tokens on hardware you own (Ollama, llama.cpp, vLLM, LM Studio) from watts, electricity price, hardware price and measured tokens/second, and the utilisation at…
OpenRouter real spend — key limit and usage today/week/month, one request's billed cost by generation id, account credits.
Run a ruflo swarm agent on the user's own ruOS cloud desktop through the fleet MCP, stream its output and record it in swarm state.
Manage `@metaharness/darwin` bench suites — `bench create <repo>` scaffolds a JSON suite from a repo's test corpus; `bench verify <suite.json>` checks suite well-formedness.
One cost view across Claude Code, Codex and Grok on this machine — spend, tokens, cache hit ratio per provider and model, with unpriced models flagged.
Coordinate with the open ruflo swarm federation at x.ruv.io (signed Nostr, membership-gated) and ask Seraphina — the swarm queen / primary coordinator — for guidance.
7-section repo readiness report from `metaharness genome <path>`. Returns repo_type / agent_topology / risk_score / mcp_surface / test_confidence / publish_readiness.
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…
MAD-based outlier detection on session spend. Robust to the very outliers it hunts (unlike mean+sigma).
Run `@metaharness/darwin evolve <repo>` to mutate a harness's seven policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy),…
Composite CI gate — runs cost-budget-check + cost-burn + cost-anomaly + cost-projection in parallel and surfaces a single combined health status with max exit code.
Mean-variance portfolio optimization via Conjugate Gradient — 40-60× faster than the legacy Neumann path (ADR-126 Phase 3, ADR-123 Wedge 8)
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
Optimisation findings from your own Claude Code and Codex logs — low cache hit ratio, 1-hour cache writes that did not pay back, sub-agents on a top-tier model, Codex reasoning…
One-command drift detection. Composes audit-list + oia-audit + audit-trend into a single primitive — finds the most recent audit in `metaharness-audit` namespace, runs a fresh…
Composite Phase-2 audit worker (ADR-150). Bundles harness oia-manifest + threat-model + mcp-scan into one timestamped audit record stored in the `metaharness-audit` memory…
Run a GEPA learning cycle via `metaharness learn` (upstream ADR-235,
[email protected]) — optimizes a harness genome against a SWE-bench-style slice manifest.
Generate a new song from a creative brief (genre, mood, language, BPM, theme) via the cogmusic MCP create_production tool
Diagnose why a GAIA question failed — extract trace, classify failure mode, and propose a fix
Forward-looking spend extrapolation. Computes a USD-per-day rate from the recent measurement window, projects to 7d/30d/90d/365d horizons, and surfaces "days until budget…
Tell apart and check the RuVLLM packages — the WASM add-on behind ruvllm_* tools, the @ruvector/ruvllm 4.1 native runtime and the GPU-loop harness.
Static security scan of a harness's declared MCP surface via `harness mcp-scan <path>`. Reads `.mcp/servers.json` + `.harness/claims.json`. Pure-read, no dispatch.
Scaffold a custom AI agent harness via `metaharness new <name> --template <id> --host <id>`. Defaults to DRY-RUN (no writes) unless --confirm is passed.
Spawn nested sub-agents (agents that spawn sub-agents, up to depth=5) via Claude Code's native Task tool — for context-managed deep delegation
Run one tick of the sales business-pod (ADR-164 §4.1, Phase 2). Loads templates/sales.json, validates it against the pod-schema, resolves agents against ruflo's agent registry,…
One-time setup — mint a Cognitum Music personal access token and register the cogmusic MCP server with Claude Code
Walk through a complete GAIA benchmark→submit flow — from key resolution through HAL-compatible package generation
Run a mastering pass (LUFS loudness normalization + peak limiting) on an existing production
Per-message cost breakdown within a single session. The drill-down companion to cost-anomaly — when an outlier session is flagged, this surfaces the specific expensive messages so…
Join and operate a signed cross-host agentbbs federation and coordinate work claims across nodes. Use when connecting ruflo agents across machines, sharing tasks or results…
Execute a natural-language browser intent via page-agent (browser_act) when the target is easier to describe than to select — degrades gracefully when page-agent or an…
5-dimension harness readiness scorecard from `metaharness score <path>`. Returns harnessFit / compileConfidence / taskCoverage / toolSafety / memoryUsefulness + estCostPerRunUsd +…
Discover and run bounded remote dynamic workflows with Ruflo mod policy, worker inspection and independent acceptance gates
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,…
Scaffold a Claude Code mod (a plugin with a function-hooks module) from ruflo's governed template, then validate and test it.
Run `@metaharness/darwin security bench` (upstream "Darwin Shield" / ADR-155) — evolves a champion security-detection harness against a 10-vuln / 9-decoy corpus and grades it on…
Snapshot delta between two cost-summary JSON outputs. PR-level cost regression detection — answers "what changed between these two specific snapshots?".
Run an Anthropic Claude Managed Agent — a cloud agent harness (container + filesystem + tools), the cloud counterpart of the local wasm-agent runtime
Enterprise-review-grade threat model from `harness threat-model <path>`. Categorizes MCP-surface threats; emits `worst: 'clean'|'low'|'medium'|'high'` + per-threat findings.
Test-Driven Repair — given a failing test, spawn a bounded headless `claude -p` (Read/Edit/Bash only) that makes the test pass without modifying it.
Inspect and audit GEPA genomes via the `@metaharness/darwin/gepa` library entry (darwin 0.8.0) — load/validate a genome (default: the shipped cand-6 promotion), render the system…
Run Ruflo-style named Agent Teams on Grok Build using the host-agnostic team bus (scripts/grok-team-bus.mjs).
Screen what goes into AgentDB memory for prompt injection with the opt-in aidefence guard (AGENTDB_INJECTION_GUARD=warn|block).
Show AgentDB health — pattern count, embedder status, cache hit rate, learning gain since init. Use when the user asks "is agentdb working?", "how many memories?", "show agentdb…
Create and run custom background analysis workers with composable phases. Use when you need automated code analysis, security scanning, pattern learning, or API documentation…
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, and hybrid search for distributed AI systems.
Stores approved context for one AI team and searches it later, with provenance. Use when the user asks to remember a decision, constraint, or fact for the team, or to recall what…
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying.
Coordinate work across a RuFlo AI-agent swarm by discovering channels, reading signed updates, checking claims, and choosing safe next actions.
Train RuView models — camera-free WiFlow pose (10 sensor signals, no labels), camera-supervised pose (MediaPipe + ESP32 CSI → 92.9% PCK@20, ADR-079), RuVector contrastive…