Agentic Quality Engineering Fleet

---

⚡ Quick Start

Install & Initialize

# Install globally
npm install -g agentic-qe

# Initialize your project
cd your-project
aqe init

# Add MCP server to Claude Code (optional)
claude mcp add agentic-qe npx aqe-mcp

# Verify connection
claude mcp list

Use from Claude Code CLI

Ask Claude to use AQE agents directly from your terminal:

# Generate comprehensive tests
claude "Use qe-test-generator to create tests for src/services/user-service.ts with 95% coverage"

# Run quality pipeline
claude "Initialize AQE fleet: generate tests, execute them, analyze coverage, and run quality gate"

# Detect flaky tests
claude "Use qe-flaky-test-hunter to analyze the last 100 test runs and identify flaky tests"

What gets initialized:

• ✅ Real-time Visualization: Dashboards, interactive graphs, WebSocket streaming
• ✅ Observability Stack: OpenTelemetry, Event Store, Constitution System
• ✅ HybridRouter: Intelligent LLM routing with 70-81% cost savings
• ✅ Self-Learning System: Agents improve with every task (20% target)
• ✅ Pattern Bank: Cross-project pattern reuse (85%+ matching)
• ✅ ML Flaky Detection: 90%+ accuracy with root cause analysis
• ✅ 21 QE Agents: Including Code Intelligence (80% token reduction)
• ✅ 15 n8n Agents: Workflow testing by @fndlalit
• ✅ 11 TDD Subagents: RED/GREEN/REFACTOR phases
• ✅ 46 QE Skills: Including testability-scoring by @fndlalit
• ✅ 8 Slash Commands: Quick access to common workflows

Optional Configuration (.env):

# Enable advanced features (see .env.example)
LLM_MODE=hybrid              # Cost-optimized routing
AQE_RUVECTOR_ENABLED=true    # Self-learning with PostgreSQL

---

🎯 Why AQE?

Problem	AQE Solution
Writing comprehensive tests is tedious and time-consuming	AI agents generate tests automatically with pattern reuse across projects
Test suites become slow and expensive at scale	Sublinear O(log n) algorithms for coverage analysis and intelligent test selection
Flaky tests waste developer time debugging false failures	ML-powered detection (90%+ accuracy) with root cause analysis and fix recommendations
AI testing tools are expensive	Multi-model routing cuts costs by up to 70-81% by matching task complexity to model
No memory between test runs—every analysis starts from scratch	Self-learning system remembers patterns, strategies, and what works for your codebase
Agents waste tokens reading irrelevant code	Code Intelligence provides 80% token reduction with semantic search and knowledge graphs
Tools don't understand your testing frameworks	Works with Jest, Cypress, Playwright, Vitest, Mocha, Jasmine, AVA

---

✨ Features

🧠 Self-Learning Agents That Get Smarter

Unlike traditional testing tools that start from scratch every run, AQE agents build institutional knowledge for your codebase:

What Gets Learned	Benefit
Test patterns that work for your framework	85%+ pattern reuse across projects
Optimal strategies for your codebase structure	Faster, more relevant test generation
Failure patterns and how to prevent them	Proactive defect prevention
Cost-effective routing decisions	Automatic budget optimization

4 Reinforcement Learning Algorithms: Q-Learning (default), SARSA, Actor-Critic (A2C), PPO

# Check what your agents have learned
aqe learn status --agent qe-test-generator
aqe patterns list --framework jest

---

💰 70-81% Cost Savings with Intelligent Routing

HybridRouter automatically matches task complexity to the right model:

Task Type	Model Selected	Cost
Simple (formatting, syntax)	Claude Haiku / GPT-3.5	$0.25/M
Moderate (unit tests, refactoring)	Claude Sonnet / GPT-4 Turbo	$3/M
Complex (architecture, security)	Claude Opus 4.5 / GPT-5	$15/M
Reasoning-heavy	DeepSeek R1 / o1-preview	Varies

25+ December 2025 models including Claude Opus 4.5, DeepSeek R1 (671B), GPT-5, Gemini 2.5 Pro

---

🤖 48 Specialized QE Agents

Category	Agents	Highlights
Core QE	21 agents	Test generation, coverage, security, performance, accessibility
TDD Workflow	11 subagents	RED/GREEN/REFACTOR phases with coordination
n8n Workflow Testing	15 agents	Chaos, compliance, security, BDD scenarios
Base	1 template	Create custom agents

Zero external dependencies - Native hooks system runs 100-500x faster than external coordination

---

🎯 ML-Powered Flaky Test Detection

90%+ accuracy with automated root cause analysis:

• Statistical pattern detection across test runs
• Timing analysis and race condition identification
• Auto-fix recommendations with code suggestions
• Integration with CI/CD for continuous monitoring

claude "Use qe-flaky-test-hunter to analyze the last 100 test runs"

---

🔍 Code Intelligence (80% Token Reduction)

Stop wasting tokens on irrelevant code. Semantic search + knowledge graphs deliver only what matters:

• Tree-sitter parsing for TypeScript, Python, Go, Rust, JavaScript
• Hybrid search: BM25 + vector similarity with <10ms latency
• RAG context building for LLM queries
• Mermaid visualization of code relationships

aqe kg index src/          # Index your codebase
aqe kg search "auth flow"  # Semantic search

---

📊 Real-Time Visualization

See your agents work with live dashboards:

• MindMap: 1000+ nodes, <500ms render, WebSocket updates
• Quality Radar: 7-dimension chart (coverage, security, performance)
• Timeline: Virtual scrolling for 1000+ events
• Grafana: Executive, Developer, and QA dashboards

Performance: 185 events/sec throughput, <1ms query latency

---

🎓 46 World-Class QE Skills

95%+ coverage of modern QE practices - agents automatically apply relevant skills:

View All 46 Skills

Core Testing & Methodologies

• agentic-quality-engineering, holistic-testing-pact, context-driven-testing
• tdd-london-chicago, xp-practices, risk-based-testing, test-automation-strategy

Specialized Testing

• accessibility-testing, mobile-testing, database-testing, contract-testing
• chaos-engineering-resilience, visual-testing-advanced, compliance-testing

Strategic & Communication

• six-thinking-hats, brutal-honesty-review, sherlock-review
• cicd-pipeline-qe-orchestrator, bug-reporting-excellence

n8n Workflow Testing (contributed by @fndlalit)

• n8n-workflow-testing, n8n-expression-testing, n8n-security-testing

Unique Skills

• testability-scoring - Score code testability before writing tests
• qx-partner - QA + UX collaboration for quality experience

---

📦 Multi-Framework Support

Works with your existing tools:

Category	Supported
Unit Testing	Jest, Mocha, Vitest, Jasmine, AVA
E2E Testing	Cypress, Playwright
Performance	k6, JMeter, Gatling
Code Quality	ESLint, SonarQube, Lighthouse

Parallel execution: 10,000+ concurrent tests with intelligent orchestration

---

💻 Usage Examples

Example 1: Single Agent Execution

Ask Claude to use a specific agent:

claude "Use the qe-test-generator agent to create comprehensive tests for src/services/user-service.ts with 95% coverage"

What happens:

1. Claude Code spawns qe-test-generator via Task tool
2. Agent analyzes the source file
3. Generates tests with pattern matching (Phase 2 feature)
4. Stores results in memory at aqe/test-plan/generated

Output:

Generated 42 tests
Pattern hit rate: 67%
Time saved: 2.3s
Quality score: 96%

Example 2: Multi-Agent Parallel Execution

Coordinate multiple agents at once:

claude "Initialize the AQE fleet:
1. Use qe-test-generator to create tests for src/services/*.ts
2. Use qe-test-executor to run all tests in parallel
3. Use qe-coverage-analyzer to find gaps with sublinear algorithms
4. Use qe-quality-gate to validate against 95% threshold"

What happens:

1. Claude spawns 4 agents concurrently in a single message
2. Agents coordinate through aqe/* memory namespace
3. Pipeline: tes