ruflo 3.10.5 → 3.10.7

package/README.md

@@ -202,7 +202,7 @@ claude mcp add ruflo -- npx ruflo@latest mcp start
 | 📡 **Comms Layer** | Zero-trust federation — agents across machines/orgs discover, authenticate, and exchange work securely |
 | 🐝 **Swarm Coordination** | Hierarchical, mesh, and adaptive topologies with consensus |
 | 🧠 **Self-Learning** | SONA neural patterns, ReasoningBank, trajectory learning |
-| 💾 **Vector Memory** | HNSW-indexed AgentDB with 150x-12,500x faster search |
+| 💾 **Vector Memory** | HNSW-indexed AgentDB — measured ~1.9x faster at N=20k, ~3.2x–4.7x at N=5k vs brute force (recall@10 ~0.99); ANN wins above the crossover, ties/loses at small N. See [audit](docs/reviews/intelligence-system-audit-2026-05-29.md) + [`scripts/benchmark-intelligence.mjs`](scripts/benchmark-intelligence.mjs) |
 | ⚡ **Background Workers** | 12 auto-triggered workers (audit, optimize, testgaps, etc.) |
 | 🧩 **Plugin Marketplace** | 32 native Claude Code plugins + 21 npm plugins |
 | 🔌 **Multi-Provider** | Claude, GPT, Gemini, Cohere, Ollama with smart routing |
@@ -228,7 +228,7 @@ claude mcp add ruflo -- npx ruflo@latest mcp start
 | 🛠️ | **~210 tools, ready to call** | 5 server groups (Core, Intelligence, Agents, Memory, DevTools) plus an 18-tool gallery that runs entirely in your browser — works offline. |
 | 🔌 | **Bring your own MCP servers** | Click the **MCP (n)** pill in the chat input → *Add Server* and paste any MCP endpoint (HTTP, SSE, or stdio). Your tools join RuFlo's native ones in the same parallel-execution flow. Run a local MCP server on `localhost:3000` and it just works. |
 | ⚡ | **Tools run in parallel** | One model response can fire 4–6+ tools at the same time. The UI shows them as cards with a *Step 1 — 2 tools completed* badge so you can see exactly what ran. |
-| 💾 | **Memory that sticks** | Say *"remember my favorite color is indigo"* and ask weeks later — RuFlo recalls it. Backed by AgentDB + HNSW vector search (≥150× faster than brute force). |
+| 💾 | **Memory that sticks** | Say *"remember my favorite color is indigo"* and ask weeks later — RuFlo recalls it. Backed by AgentDB + HNSW vector search (measured ~1.9x–4.7x faster than brute force above the crossover, recall@10 ~0.99). |
 | 📘 | **Built-in capabilities tour** | Click the question-mark icon in the sidebar — a "RuFlo Capabilities" modal opens with the full tool list, model strengths, architecture, and keyboard shortcuts. |
 | 🏠 | **Self-hostable** | Web UI is shipped as Docker (`ruflo/src/ruvocal/Dockerfile`) with embedded Mongo. Deploy to your own Cloud Run / Fly / Kubernetes / docker-compose. The hosted [flo.ruv.io](https://flo.ruv.io/) demo is one option; running your own is fully supported. |
 | 🚀 | **Zero install to try** | Open the hosted URL, pick a model, type a question. That's the whole onboarding. |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ruflo",
-  "version": "3.10.5",
+  "version": "3.10.7",
   "description": "Ruflo - Enterprise AI agent orchestration platform. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration",
   "main": "bin/ruflo.js",
   "type": "module",
@@ -43,6 +43,7 @@
     "@claude-flow/cli": "^3.10.3"
   },
   "overrides": {
+    "better-sqlite3": ">=12.8.0",
     "@ruvector/rvf-wasm": "0.1.5",
     "@hono/node-server": ">=1.19.10",
     "flatted": ">=3.4.0",

package/src/ruvocal/.claude-flow/daemon-state.json

@@ -0,0 +1,135 @@
+{
+  "running": true,
+  "startedAt": "2026-05-05T02:48:11.836Z",
+  "workers": {
+    "map": {
+      "runCount": 1,
+      "successCount": 1,
+      "failureCount": 0,
+      "averageDurationMs": 0,
+      "isRunning": false,
+      "nextRun": "2026-05-05T03:03:11.838Z",
+      "lastRun": "2026-05-05T02:48:11.838Z"
+    },
+    "audit": {
+      "runCount": 2,
+      "successCount": 2,
+      "failureCount": 0,
+      "averageDurationMs": 43209,
+      "isRunning": false,
+      "nextRun": "2026-05-05T03:00:42.275Z",
+      "lastRun": "2026-05-05T03:01:38.242Z"
+    },
+    "optimize": {
+      "runCount": 1,
+      "successCount": 1,
+      "failureCount": 0,
+      "averageDurationMs": 74039,
+      "isRunning": false,
+      "nextRun": "2026-05-05T03:08:25.861Z",
+      "lastRun": "2026-05-05T02:53:25.860Z"
+    },
+    "consolidate": {
+      "runCount": 1,
+      "successCount": 1,
+      "failureCount": 0,
+      "averageDurationMs": 0,
+      "isRunning": false,
+      "nextRun": "2026-05-05T03:24:11.821Z",
+      "lastRun": "2026-05-05T02:54:11.820Z"
+    },
+    "testgaps": {
+      "runCount": 1,
+      "successCount": 1,
+      "failureCount": 0,
+      "averageDurationMs": 141408,
+      "isRunning": false,
+      "nextRun": "2026-05-05T03:18:33.228Z",
+      "lastRun": "2026-05-05T02:58:33.228Z"
+    },
+    "predict": {
+      "runCount": 0,
+      "successCount": 0,
+      "failureCount": 0,
+      "averageDurationMs": 0,
+      "isRunning": false
+    },
+    "document": {
+      "runCount": 0,
+      "successCount": 0,
+      "failureCount": 0,
+      "averageDurationMs": 0,
+      "isRunning": false
+    }
+  },
+  "config": {
+    "autoStart": false,
+    "logDir": "/Users/cohen/Projects/ruflo/ruflo/src/ruvocal/.claude-flow/logs",
+    "stateFile": "/Users/cohen/Projects/ruflo/ruflo/src/ruvocal/.claude-flow/daemon-state.json",
+    "maxConcurrent": 2,
+    "workerTimeoutMs": 960000,
+    "resourceThresholds": {
+      "maxCpuLoad": 9.600000000000001,
+      "minFreeMemoryPercent": 5
+    },
+    "workers": [
+      {
+        "type": "map",
+        "intervalMs": 900000,
+        "offsetMs": 0,
+        "priority": "normal",
+        "description": "Codebase mapping",
+        "enabled": true
+      },
+      {
+        "type": "audit",
+        "intervalMs": 600000,
+        "offsetMs": 120000,
+        "priority": "critical",
+        "description": "Security analysis",
+        "enabled": true
+      },
+      {
+        "type": "optimize",
+        "intervalMs": 900000,
+        "offsetMs": 240000,
+        "priority": "high",
+        "description": "Performance optimization",
+        "enabled": true
+      },
+      {
+        "type": "consolidate",
+        "intervalMs": 1800000,
+        "offsetMs": 360000,
+        "priority": "low",
+        "description": "Memory consolidation",
+        "enabled": true
+      },
+      {
+        "type": "testgaps",
+        "intervalMs": 1200000,
+        "offsetMs": 480000,
+        "priority": "normal",
+        "description": "Test coverage analysis",
+        "enabled": true
+      },
+      {
+        "type": "predict",
+        "intervalMs": 600000,
+        "offsetMs": 0,
+        "priority": "low",
+        "description": "Predictive preloading",
+        "enabled": false
+      },
+      {
+        "type": "document",
+        "intervalMs": 3600000,
+        "offsetMs": 0,
+        "priority": "low",
+        "description": "Auto-documentation",
+        "enabled": false
+      }
+    ]
+  },
+  "savedAt": "2026-05-05T03:01:38.242Z"
+}

package/src/ruvocal/.claude-flow/data/ranked-context.json

@@ -0,0 +1,5 @@
+{
+  "version": 1,
+  "computedAt": 1777949290620,
+  "entries": []
+}

package/src/ruvocal/.claude-flow/logs/daemon.log

@@ -0,0 +1,31 @@
+[2026-05-05T02:48:11.836Z] [INFO] Scheduled map (interval: 900s, first run in 0s)
+[2026-05-05T02:48:11.837Z] [INFO] Scheduled audit (interval: 600s, first run in 120s)
+[2026-05-05T02:48:11.837Z] [INFO] Scheduled optimize (interval: 900s, first run in 240s)
+[2026-05-05T02:48:11.837Z] [INFO] Scheduled consolidate (interval: 1800s, first run in 360s)
+[2026-05-05T02:48:11.837Z] [INFO] Scheduled testgaps (interval: 1200s, first run in 480s)
+[2026-05-05T02:48:11.837Z] [INFO] Daemon started (PID: 78051, CPUs: 12, workers: 5, maxCpuLoad: 9.600000000000001, minFreeMemoryPercent: 5%)
+[2026-05-05T02:48:11.837Z] [INFO] Claude Code headless mode available - AI workers enabled
+[2026-05-05T02:48:11.838Z] [INFO] Starting worker: map (1/2 concurrent)
+[2026-05-05T02:48:11.838Z] [INFO] Worker map completed in 0ms
+[2026-05-05T02:50:11.821Z] [INFO] Starting worker: audit (1/2 concurrent)
+[2026-05-05T02:50:11.822Z] [INFO] Running audit in headless mode (Claude Code AI)
+[2026-05-05T02:50:14.769Z] [INFO] Daemon already running (PID: 78051), skipping start
+[2026-05-05T02:50:14.769Z] [INFO] Claude Code headless mode available - AI workers enabled
+[2026-05-05T02:50:42.274Z] [INFO] Worker audit completed in 30453ms
+[2026-05-05T02:52:11.821Z] [INFO] Starting worker: optimize (1/2 concurrent)
+[2026-05-05T02:52:11.822Z] [INFO] Running optimize in headless mode (Claude Code AI)
+[2026-05-05T02:52:13.244Z] [INFO] Daemon already running (PID: 78051), skipping start
+[2026-05-05T02:52:13.244Z] [INFO] Claude Code headless mode available - AI workers enabled
+[2026-05-05T02:53:25.860Z] [INFO] Worker optimize completed in 74039ms
+[2026-05-05T02:54:11.820Z] [INFO] Starting worker: consolidate (1/2 concurrent)
+[2026-05-05T02:54:11.820Z] [INFO] Worker consolidate completed in 0ms
+[2026-05-05T02:56:11.820Z] [INFO] Starting worker: testgaps (1/2 concurrent)
+[2026-05-05T02:56:11.821Z] [INFO] Running testgaps in headless mode (Claude Code AI)
+[2026-05-05T02:56:13.270Z] [INFO] Daemon already running (PID: 78051), skipping start
+[2026-05-05T02:56:13.270Z] [INFO] Claude Code headless mode available - AI workers enabled
+[2026-05-05T02:58:33.228Z] [INFO] Worker testgaps completed in 141408ms
+[2026-05-05T03:00:42.277Z] [INFO] Starting worker: audit (1/2 concurrent)
+[2026-05-05T03:00:42.278Z] [INFO] Running audit in headless mode (Claude Code AI)
+[2026-05-05T03:00:44.862Z] [INFO] Daemon already running (PID: 78051), skipping start
+[2026-05-05T03:00:44.862Z] [INFO] Claude Code headless mode available - AI workers enabled
+[2026-05-05T03:01:38.242Z] [INFO] Worker audit completed in 55965ms