<div align="center">

🚀 AgentStack

Home Networks Custom Tool v1.0.0

AgentStack is a production-grade multi-agent framework built on Mastra, delivering 57 enterprise tools, 41 specialized agents, 21 workflows, 11 agent networks, 105 UI components (50+ AI Elements + 55+ base), and A2A/MCP orchestration for scalable AI systems. Focuses on financial intelligence, RAG pipelines, observability, secure governance, and AI chat interfaces.

</div>

🎯 Why AgentStack?

AgentStack bridges the gap between experimental AI frameworks and production-ready systems. While other frameworks focus on prototyping, AgentStack delivers the observability, security, and scalability required for enterprise deployment.

| Feature | AgentStack | LangChain | CrewAI | AutoGen | | ----------------------------- | --------------------------------------------------------------- | ------------- | ------------- | ---------- | | Production Observability | ✅ Full Langfuse tracing + 10+ custom scorers | ⚠️ Partial | ❌ Basic | ❌ Limited | | Financial Intelligence | ✅ Polygon/Finnhub/AlphaVantage (30+ endpoints) | ❌ None | ❌ None | ❌ None | | RAG Pipeline | ✅ PgVector HNSW + rerank + graphRAG | ⚠️ External | ❌ Basic | ❌ None | | Multi-Agent Orchestration | ✅ A2A MCP + parallel execution (41 agents) | ⚠️ Sequential | ✅ Sequential | ✅ Custom | | Enterprise Security | ✅ JWT/RBAC + path traversal protection + HTML sanitization | ❌ Custom | ❌ None | ❌ None | | Type Safety | ✅ Zod schemas everywhere (57 tools) | ⚠️ JS/TS mix | ⚠️ JS focus | ❌ Python | | UI Components | ✅ 105 components (AI Elements + shadcn/ui) | ❌ None | ❌ None | ❌ None | | Testing | ✅ Vitest + 97% coverage + comprehensive mocks | ⚠️ Partial | ❌ Sparse | ⚠️ Partial |

🚀 Production-Ready from Day One

Zero-config RAG: PgVector with 3072D embeddings works out of the box
Enterprise APIs: First-class support for financial data providers
Full Observability: Every agent call, tool execution, and workflow step is traced
Type Safety: Strict TypeScript with Zod validation on all boundaries

✨ Core Capabilities

💰 Financial Intelligence: 30+ tools (Polygon quotes/aggs/fundamentals, Finnhub analysis, AlphaVantage indicators)
🔍 Semantic RAG: PgVector (3072D embeddings) + MDocument chunking + rerank + graph traversal
🤖 41 Agents: Research → Learn → Report → Edit → Analyze (stock/crypto/copywriter/evaluator/data pipeline/business-legal/charting/image/coding/dane/social media/SEO/translation/customer support/project management)
📋 21 Workflows: Weather, content, financial reports, document processing, research synthesis, learning extraction, governed RAG (index + answer), spec generation, repo ingestion, stock analysis, marketing campaign
🌐 11 Agent Networks: Primary routing, data pipeline, report generation, research pipeline, content creation, financial intelligence, learning, marketing automation, DevOps, business intelligence, security
🔌 A2A/MCP: MCP server coordinates parallel agents (research+stock→report), A2A coordinator for cross-agent communication
🎨 105 UI Components: AI Elements (50 chat/reasoning/canvas components) + shadcn/ui (55 base primitives)
📊 Full Observability: Langfuse traces + 10+ custom scorers (diversity/quality/completeness) + TanStack Query for state management
🛡️ Enterprise Security: JWT auth, RBAC, path validation, HTML sanitization, secrets masking
⚡ Extensible: Model registry (Gemini/OpenAI/Anthropic/OpenRouter), Zod schemas everywhere, MastraClient SDK integration

🌟 Feature Highlights

💰 Financial Intelligence Suite

Real-time market data from 30+ endpoints:

// Example: Multi-source stock analysis
const analysis = await stockAnalysisAgent.execute({
    symbol: 'AAPL',
    includeFundamentals: true,
    includeNews: true,
    timeRange: '1Y',
})
// → Combines Polygon quotes, Finnhub analysis, AlphaVantage indicators
// → Returns: Price action, valuation metrics, sentiment analysis

Supported Data Providers:

Polygon.io: Real-time quotes, historical aggregates, fundamentals
Finnhub: Company profiles, insider transactions, earnings surprises
Alpha Vantage: Technical indicators (RSI, MACD, Bollinger Bands)

🔍 Production RAG Pipeline

Zero-config semantic search with PgVector:

// 1. Index documents
await documentProcessingWorkflow.execute({
    documents: ['./annual-report.pdf', './market-data.csv'],
    chunkingStrategy: 'semantic',
    indexName: 'financial-reports',
})

// 2. Query with context
const answer = await governedRagAnswerWorkflow.execute({
    query: 'What were Q3 revenue drivers?',
    indexName: 'financial-reports',
    rerankTopK: 5,
})
// → Returns: Synthesized answer + source citations + confidence score

Features:

10 Chunking Strategies: Semantic, recursive, markdown-aware
3072D Embeddings: Gemini embedding-001
Hybrid Search: Vector similarity + BM25 reranking
Graph Traversal: Relationship-aware context expansion

🤖 Agent Networks

Parallel multi-agent orchestration:

// Research + Analysis + Report in parallel
const result = await researchPipelineNetwork.execute({
    query: 'Analyze renewable energy market trends',
    agents: ['research', 'learning', 'knowledge', 'synthesis'],
    parallel: true,
})
// → 4 agents work simultaneously, results merged by coordinator

Pre-configured Networks:

Coding Team: Architect

AgentStack

Install / Use

README