π The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
Checkpoint: File edits
rUvb1c9b4025dca
diff --git a/package-lock.json b/package-lock.jsonindex 5b1a59cb45..3f39088b7b 100644--- a/package-lock.json+++ b/package-lock.json@@ -1,12 +1,12 @@{"name": "claude-flow",- "version": "3.1.0-alpha.26",+ "version": "3.1.0-alpha.27","lockfileVersion": 3,"requires": true,"packages": {"": {"name": "claude-flow",- "version": "3.1.0-alpha.26",+ "version": "3.1.0-alpha.27","license": "MIT","dependencies": {"semver": "^7.6.0",diff --git a/package.json b/package.jsonindex 8ecf62ca23..41da87e9ab 100644--- a/package.json+++ b/package.json@@ -1,6 +1,6 @@{"name": "claude-flow",- "version": "3.1.0-alpha.26",+ "version": "3.1.0-alpha.27","description": "Enterprise AI agent orchestration for Claude Code - Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration","main": "dist/index.js","type": "module",diff --git a/v3/@claude-flow/cli/.claude/helpers/hook-handler.cjs b/v3/@claude-flow/cli/.claude/helpers/hook-handler.cjsindex 1c15614d52..8b6190bd40 100644--- a/v3/@claude-flow/cli/.claude/helpers/hook-handler.cjs+++ b/v3/@claude-flow/cli/.claude/helpers/hook-handler.cjs@@ -120,7 +120,7 @@ const handlers = {'post-edit': () => {// Record edit for session metricsif (session && session.metric) {- session.metric('edits');+ try { session.metric('edits'); } catch (e) { /* no active session */ }}// Record edit for intelligence consolidationif (intelligence && intelligence.recordEdit) {diff --git a/v3/@claude-flow/cli/README.md b/v3/@claude-flow/cli/README.mdindex 9ea20b201d..14b4d73d76 100644--- a/v3/@claude-flow/cli/README.md+++ b/v3/@claude-flow/cli/README.md@@ -616,6 +616,13 @@ codex mcp add ruflo -- npx ruflo mcp start4. REMEMBER: memory_store(key, value, namespace="patterns") β Save for future```+The **Intelligence Loop** (ADR-050) automates this cycle through hooks. Each session automatically:+- Builds a knowledge graph from memory entries (PageRank + Jaccard similarity)+- Injects ranked context into every route decision+- Tracks edit patterns and generates new insights+- Boosts confidence for useful patterns, decays unused ones+- Saves snapshots so you can track improvement with `node .claude/helpers/hook-handler.cjs stats`+### MCP Tools for Learning| Tool | Purpose | When to Use |@@ -2886,6 +2893,101 @@ Performance: <1ms (352x faster than LLM)Cost: $0```+### Intelligence Loop (ADR-050)++The intelligence loop wires PageRank-ranked memory into the hook system. Every session builds a knowledge graph that improves over time:++```+SessionStart:+ session-restore β intelligence.init()+ β Read MEMORY.md / auto-memory-store.json+ β Build graph (nodes + similarity/temporal edges)+ β Compute PageRank+ β "[INTELLIGENCE] Loaded 13 patterns, 12 edges"++UserPrompt:+ route β intelligence.getContext(prompt)+ β Jaccard-match prompt against pre-ranked entries+ β Inject top-5 patterns into Claude's context:++ [INTELLIGENCE] Relevant patterns for this task:+ * (0.95) HNSW gives 150x-12,500x speedup [rank #1, 12x accessed]+ * (0.88) London School TDD preferred [rank #3, 8x accessed]++PostEdit:+ post-edit β intelligence.recordEdit(file)+ β Append to pending-insights.jsonl (<2ms)++SessionEnd:+ session-end β intelligence.consolidate()+ β Process pending insights (3+ edits β new entry)+ β Confidence boost for accessed patterns (+0.03)+ β Confidence decay for unused patterns (-0.005/day)+ β Recompute PageRank, rebuild edges+ β Save snapshot for trend tracking+```++**Measuring improvement:**++```bash+# Human-readable diagnostics+node .claude/helpers/hook-handler.cjs stats++# JSON output for scripting+node .claude/helpers/hook-handler.cjs stats --json++# Or via intelligence.cjs directly+node .claude/helpers/intelligence.cjs stats+```++The stats command shows:++| Section | What It Tells You |+|---------|-------------------|+| **Graph** | Node/edge count, density % |+| **Confidence** | Min/max/mean/median across all patterns |+| **Access** | Total accesses, patterns used vs never accessed |+| **PageRank** | Sum (~1.0), highest-ranked node |+| **Top Patterns** | Top 10 by composite score with access counts |+| **Last Delta** | Changes since previous session (confidence shift, access delta) |+| **Trend** | Over all sessions: IMPROVING / DECLINING / STABLE |++**Example output:**+```++--------------------------------------------------------------++| Intelligence Diagnostics (ADR-050) |++--------------------------------------------------------------+++ Graph+ Nodes: 9+ Edges: 8 (7 temporal, 1 similar)+ Density: 22.2%++ Confidence+ Min: 0.490 Max: 0.600+ Mean: 0.556 Median: 0.580++ Access+ Total accesses: 11+ Patterns used: 6/9+ Never accessed: 3++ Top Patterns (by composite score)+ #1 HNSW gives 150x-12,500x speedup+ conf=0.600 pr=0.2099 score=0.3659 accessed=2x+ #2 London School TDD preferred+ conf=0.600 pr=0.1995 score=0.3597 accessed=2x++ Last Delta (5m ago)+ Confidence: +0.0300+ Accesses: +6++ Trend (3 snapshots)+ Confidence drift: +0.0422+ Direction: IMPROVING++--------------------------------------------------------------++```+### All 27 Hooks by Category#### π§ Tool Lifecycle Hooks (6 hooks)@@ -2954,7 +3056,7 @@ npx ruflo@v3alpha hooks session-end --export-metrics --persist-patterns| `trajectory-end` | RL | Finish recording, trigger learning || `pattern-store` | Memory | Store a pattern with HNSW indexing || `pattern-search` | Memory | Find similar patterns (150x faster) |-| `stats` | Analytics | Learning statistics and metrics |+| `stats` | Analytics | Intelligence diagnostics, confidence trends, improvement tracking || `attention` | Focus | Compute attention-weighted similarity |```bash@@ -2966,6 +3068,10 @@ npx ruflo@v3alpha hooks intelligence trajectory-step --action "created token ser# End trajectory and trigger learningnpx ruflo@v3alpha hooks intelligence trajectory-end --success true++# View intelligence diagnostics and improvement trends (ADR-050)+node .claude/helpers/hook-handler.cjs stats+node .claude/helpers/intelligence.cjs stats --json```### 12 Background Workers (Auto-Triggered)@@ -3033,7 +3139,7 @@ npx ruflo@v3alpha hooks model-route --task "design distributed consensus system"# MOST COMMON HOOKS# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ-# Route task to best agent+# Route task to best agent (with intelligence context injection)npx ruflo@v3alpha hooks route "<task>" --include-explanation# Start/end session with learning@@ -3044,6 +3150,11 @@ npx ruflo@v3alpha hooks session-end --persist-patternsnpx ruflo@v3alpha hooks metricsnpx ruflo@v3alpha hooks intelligence stats+# Intelligence diagnostics β see if intelligence is improving+node .claude/helpers/hook-handler.cjs stats # Human-readable+node .claude/helpers/hook-handler.cjs stats --json # JSON for scripting+node .claude/helpers/intelligence.cjs stats # Direct access+# Bootstrap on new projectnpx ruflo@v3alpha hooks pretrain --depth deepdiff --git a/v3/@claude-flow/cli/package.json b/v3/@claude-flow/cli/package.jsonindex e5485699cb..521dc25901 100644--- a/v3/@claude-flow/cli/package.json+++ b/v3/@claude-flow/cli/package.json@@ -1,6 +1,6 @@{"name": "@claude-flow/cli",- "version": "3.1.0-alpha.26",+ "version": "3.1.0-alpha.27","type": "module","description": "Claude Flow CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code","main": "dist/src/index.js",