claude-flow 3.0.0-alpha.7 → 3.0.0-alpha.71

package/README.md

@@ -4,7 +4,7 @@
 
 [![Star on GitHub](https://img.shields.io/github/stars/ruvnet/claude-flow?style=for-the-badge&logo=github&color=gold)](https://github.com/ruvnet/claude-flow)
 [![Downloads](https://img.shields.io/npm/dt/claude-flow?style=for-the-badge&logo=npm&color=blue&label=Downloads)](https://www.npmjs.com/package/claude-flow)
-[![Latest Release](https://img.shields.io/npm/v/claude-flow/alpha?style=for-the-badge&logo=npm&color=green&label=v2.7.0-alpha.10)](https://www.npmjs.com/package/claude-flow)
+[![Latest Release](https://img.shields.io/npm/v/claude-flow/alpha?style=for-the-badge&logo=npm&color=green&label=v3.0.0-alpha)](https://www.npmjs.com/package/claude-flow)
 [![Claude Code](https://img.shields.io/badge/Claude%20Code-SDK%20Integrated-green?style=for-the-badge&logo=anthropic)](https://github.com/ruvnet/claude-flow)
 [![Agentics Foundation](https://img.shields.io/badge/Agentics-Foundation-crimson?style=for-the-badge&logo=openai)](https://discord.com/invite/dfxmpwkG2D)
 [![MIT License](https://img.shields.io/badge/License-MIT-yellow?style=for-the-badge&logo=opensourceinitiative)](https://opensource.org/licenses/MIT)
@@ -48,6 +48,61 @@ Claude-Flow is a comprehensive AI agent orchestration framework that transforms
 
 - **Production-Ready Security** - Built-in protection against common vulnerabilities: input validation, path traversal prevention, command injection blocking, and safe credential handling.
 
+### Why Claude-Flow v3?
+
+Claude-Flow v3 introduces **self-learning neural capabilities** that no other agent orchestration framework offers. While competitors require manual agent configuration and static routing, Claude-Flow learns from every task execution, prevents catastrophic forgetting of successful patterns, and intelligently routes work to specialized experts.
+
+| Feature | Claude Flow v3 | CrewAI | LangGraph | AutoGen | MetaGPT |
+|---------|----------------|--------|-----------|---------|---------|
+| **Self-Learning** | SONA + EWC++ | - | - | - | - |
+| **Prevents Forgetting** | EWC++ consolidation | - | - | - | - |
+| **Expert Routing** | MoE (8 experts) | Manual roles | Graph edges | - | Fixed roles |
+| **Vector Memory** | HNSW (150x faster) | - | Via plugins | - | - |
+| **Hyperbolic Embeddings** | Poincaré ball model | - | - | - | - |
+| **Pattern Learning** | From trajectories | - | - | - | - |
+| **Work Ownership** | Claims system | - | - | - | - |
+| **Threat Detection** | AIDefence | - | - | - | - |
+| **Attention Optimization** | Flash Attention | - | - | - | - |
+| **Low-Rank Adaptation** | LoRA (128x compression) | - | - | - | - |
+| **Quantization** | Int8 (3.92x savings) | - | - | - | - |
+| **Consensus Protocols** | 5 (Raft, Byzantine, etc.) | - | - | - | - |
+| **Background Workers** | 12 auto-triggered | - | - | - | - |
+| **Multi-Provider LLM** | 6 with failover | 2 | 3 | 2 | 1 |
+| **MCP Integration** | Native | - | - | - | - |
+| **Swarm Topologies** | 4 (mesh, hierarchical, etc.) | 1 | 1 | 1 | 1 |
+
+**Key differentiators:**
+- **SONA (Self-Optimizing Neural Architecture)** - Learns optimal agent routing from trajectory outcomes with <0.05ms adaptation
+- **EWC++ (Elastic Weight Consolidation)** - Prevents catastrophic forgetting when learning new patterns
+- **MoE (Mixture of Experts)** - 8 specialized experts with dynamic gating network for intelligent task routing
+- **Flash Attention** - 2.49x-7.47x speedup for attention computations
+- **Hyperbolic Embeddings** - Poincaré ball model for hierarchical data representation (better for code structure)
+- **LoRA (Low-Rank Adaptation)** - 128x memory compression for efficient fine-tuning
+- **Int8 Quantization** - 3.92x memory reduction with minimal accuracy loss
+- **Claims System** - Human-agent work ownership with handoff protocols
+- **Byzantine Consensus** - Fault-tolerant coordination even with malicious agents
+
+### Intelligent 3-Tier Model Routing (ADR-026)
+
+Automatically routes tasks to the optimal handler for **75% cost reduction** and **2.5x quota extension** for Claude Max users:
+
+| Tier | Handler | Latency | Cost | Use Cases |
+|------|---------|---------|------|-----------|
+| **1** | Agent Booster (WASM) | <1ms | $0 | Simple transforms: var→const, add-types, remove-console |
+| **2** | Haiku/Sonnet | 500ms-2s | $0.0002-$0.003 | Bug fixes, refactoring, feature implementation |
+| **3** | Opus | 2-5s | $0.015 | Architecture, security design, distributed systems |
+
+**Benchmark Results:** 100% accuracy, 0.57ms avg routing latency
+
+```bash
+# Example: Task automatically routed to appropriate tier
+npx claude-flow@v3alpha hooks pre-task --description "Add type annotations to server.ts"
+# → [AGENT_BOOSTER_AVAILABLE] Skip LLM - use Agent Booster for "add-types"
+
+npx claude-flow@v3alpha hooks pre-task --description "Design OAuth2 with PKCE"
+# → [TASK_MODEL_RECOMMENDATION] Use model="opus" for this task
+```
+
 ---
 
 ## Quick Start
@@ -157,6 +212,7 @@ npx claude-flow@v3alpha --list
 | **GitHub** | `github_swarm`, `repo_analyze`, `pr_enhance`, `issue_triage`, `code_review` | Repository integration |
 | **Workers** | `worker/run`, `worker/status`, `worker/alerts`, `worker/history` | Background task management |
 | **Hooks** | `hooks/pre-*`, `hooks/post-*`, `hooks/route`, `hooks/session-*`, `hooks/intelligence/*`, `hooks/worker/*` | 31 lifecycle hooks |
+| **Progress** | `progress/check`, `progress/sync`, `progress/summary`, `progress/watch` | V3 implementation tracking |
 
 ### Security Features
 
@@ -302,18 +358,21 @@ npx claude-flow@v3alpha worker results --limit 10
 
 | Provider | Models | Dimensions | Latency | Cost |
 |----------|--------|------------|---------|------|
+| **Agentic-Flow** | ONNX SIMD optimized | 384 | ~3ms | Free (local) |
 | **OpenAI** | text-embedding-3-small/large, ada-002 | 1536-3072 | ~50-100ms | $0.02-0.13/1M tokens |
-| **Transformers.js** | all-MiniLM-L6-v2, all-mpnet-base-v2, bge-small | 384-768 | ~20-50ms | Free (local) |
+| **Transformers.js** | all-MiniLM-L6-v2, all-mpnet-base-v2, bge-small | 384-768 | ~230ms | Free (local) |
 | **Mock** | Deterministic hash-based | Configurable | <1ms | Free |
 
 ### Embedding Features
 
 | Feature | Description | Performance |
 |---------|-------------|-------------|
+| **Auto-Install** | `provider: 'auto'` installs agentic-flow automatically | Zero config |
+| **Smart Fallback** | agentic-flow → transformers → mock chain | Always works |
+| **75x Faster** | Agentic-flow ONNX vs Transformers.js | 3ms vs 230ms |
 | **LRU Caching** | Intelligent cache with hit rate tracking | <1ms cache hits |
-| **Batch Processing** | Efficient batch embedding with partial cache | 10 items <500ms |
+| **Batch Processing** | Efficient batch embedding with partial cache | 10 items <100ms |
 | **Similarity Functions** | Cosine, Euclidean, Dot product | Optimized math |
-| **Event System** | Observable operations with listeners | Real-time monitoring |
 
 ### Consensus Strategies (`@claude-flow/swarm`)
 
@@ -339,9 +398,19 @@ npx claude-flow@v3alpha worker results --limit 10
 | `config` | 7 | Configuration (init, get, set, providers, reset, export, import) |
 | `status` | 3 | System status with watch mode (agents, tasks, memory) |
 | `workflow` | 6 | Workflow execution (run, validate, list, status, stop, template) |
-| `hooks` | 31 | Self-learning hooks (pre/post-edit, pre/post-command, route, explain, pretrain, session-*, intelligence/*, worker/*) |
+| `hooks` | 32 | Self-learning hooks (pre/post-edit, pre/post-command, route, explain, pretrain, session-*, intelligence/*, worker/*, progress) |
 | `hive-mind` | 6 | Queen-led coordination (init, spawn, status, task, optimize-memory, shutdown) |
 | `migrate` | 5 | V2→V3 migration (status, run, verify, rollback, breaking) |
+| `neural` | 5 | Neural pattern training (train, status, patterns, predict, optimize) |
+| `security` | 6 | Security scanning (scan, audit, cve, threats, validate, report) |
+| `performance` | 5 | Performance profiling (benchmark, profile, metrics, optimize, report) |
+| `providers` | 5 | AI providers (list, add, remove, test, configure) |
+| `plugins` | 5 | Plugin management (list, install, uninstall, enable, disable) |
+| `deployment` | 5 | Deployment management (deploy, rollback, status, environments, release) |
+| `embeddings` | 13 | Vector embeddings with ONNX, hyperbolic space, neural substrate |
+| `daemon` | 5 | Background workers (start, stop, status, trigger, enable) |
+| `progress` | 4 | V3 implementation progress (check, sync, summary, watch) |
+| `claims` | 4 | Authorization (check, grant, revoke, list) |
 
 ### Testing Framework (`@claude-flow/testing`)
 
@@ -453,11 +522,25 @@ npx claude-flow@v3alpha worker results --limit 10
 
 | Feature | Description | Performance |
 |---------|-------------|-------------|
-| **Multi-Provider** | OpenAI, Transformers.js (local), Mock | Flexible deployment |
+| **Multi-Provider** | Agentic-Flow (ONNX), OpenAI, Transformers.js, Mock | 4 providers |
+| **Auto-Install** | `claude-flow embeddings init` or `createEmbeddingServiceAsync()` | Zero config |
+| **75x Faster** | Agentic-flow ONNX SIMD vs Transformers.js | 3ms vs 230ms |
+| **Hyperbolic Space** | Poincaré ball model for hierarchical data | Exponential capacity |
 | **Dimensions** | 384 to 3072 configurable | Quality vs speed tradeoff |
-| **Similarity Metrics** | Cosine, Euclidean, Dot product | Task-specific matching |
-| **Event System** | Observable operations with listeners | Real-time monitoring |
-| **Partial Cache Hits** | Batch requests use cached where available | Reduced API calls |
+| **Similarity Metrics** | Cosine, Euclidean, Dot product, Hyperbolic distance | Task-specific matching |
+| **Neural Substrate** | Drift detection, memory physics, swarm coordination | agentic-flow integration |
+| **LRU + SQLite Cache** | Persistent cross-session caching | <1ms cache hits |
+
+```bash
+# Initialize ONNX embeddings with hyperbolic config
+claude-flow embeddings init
+
+# Use larger model for higher quality
+claude-flow embeddings init --model all-mpnet-base-v2
+
+# Semantic search
+claude-flow embeddings search -q "authentication patterns"
+```
 
 ### SONA Learning Modes
 
@@ -762,10 +845,12 @@ Shell-based daemons for monitoring (Linux/macOS only):
 | Route task | `npx claude-flow@v3alpha hooks route "Optimize database queries"` |
 | Performance analysis | `npx claude-flow@v3alpha --agent perf-analyzer --task "Profile API endpoints"` |
 | GitHub PR management | `npx claude-flow@v3alpha --agent pr-manager --task "Review open PRs"` |
+| Check V3 progress | `npx claude-flow@v3alpha progress --detailed` |
+| Sync progress metrics | `npx claude-flow@v3alpha progress sync` |
 
 ---
 
-## Self-Learning Hooks Commands (26 Hooks)
+## Self-Learning Hooks Commands (27 Hooks)
 
 ### Core Tool Lifecycle Hooks
 ```bash
@@ -867,6 +952,24 @@ npx claude-flow@v3alpha hooks worker status
 npx claude-flow@v3alpha hooks worker cancel --id worker_refactor_1_abc123
 ```
 
+### Progress Tracking Hooks
+```bash
+# Check V3 implementation progress
+npx claude-flow@v3alpha hooks progress
+
+# Detailed breakdown by category (CLI, MCP, Hooks, Packages, DDD)
+npx claude-flow@v3alpha hooks progress --detailed
+
+# Sync progress and persist to file
+npx claude-flow@v3alpha hooks progress --sync
+
+# Get human-readable summary
+npx claude-flow@v3alpha hooks progress --summary
+
+# JSON output for scripting
+npx claude-flow@v3alpha progress --json
+```
+
 ---
 
 ## Architecture
@@ -1075,7 +1178,7 @@ npx claude-flow@v3alpha hooks pretrain  # Bootstrap learning
 | `@claude-flow/integration` | agentic-flow@alpha integration | [Source](./v3/@claude-flow/integration/) |
 | `@claude-flow/performance` | Benchmarking & optimization | [Source](./v3/@claude-flow/performance/) |
 | `@claude-flow/deployment` | Release & CI/CD | [Source](./v3/@claude-flow/deployment/) |
-| `@claude-flow/shared` | Shared utilities & types | [Source](./v3/@claude-flow/shared/) |
+| `@claude-flow/shared` | Shared utilities, types & V3ProgressService | [Source](./v3/@claude-flow/shared/) |
 
 ### Additional Resources
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-flow",
-  "version": "3.0.0-alpha.7",
+  "version": "3.0.0-alpha.71",
   "description": "Claude Flow V3 - Domain-Driven Design Architecture with 15-Agent Swarm Coordination",
   "main": "dist/index.js",
   "type": "module",
@@ -33,10 +33,13 @@
     "v3:security": "npm run security:audit && npm run security:test"
   },
   "dependencies": {
-    "agentdb": "alpha",
+    "agentdb": "2.0.0-alpha.3.4",
     "bcrypt": "^5.1.1",
     "zod": "^3.22.4"
   },
+  "overrides": {
+    "hono": ">=4.11.4"
+  },
   "devDependencies": {
     "@ruvector/attention": "^0.1.3",
     "@ruvector/sona": "^0.1.5",