Welcome to AvaLangStack: Infusing Narrative and Relational Intelligence into LLM Applications
The AvaLangStack is not just a library; it’s an ecosystem designed to transform how we build and interact with LLM-powered systems. We move beyond mere function, embedding Narrative Intelligence and Indigenous Relational Paradigms at the core of AI development.
Why AvaLangStack?
In the pursuit of truly intelligent and accountable systems, traditional AI development often overlooks the profound power of narrative and the intricate web of relationality. The AvaLangStack addresses this by:
- Resolving the Tension between Logic and Life: Bridging the gap between purely logical, functional AI and systems that understand context, ethics, and the unfolding story of interaction.
- Cultivating Accountability: Our frameworks embed principles of relationality, ensuring agents operate not in isolated silos but within a holistic ecosystem of interdependence.
- Guiding with Ancient Wisdom: Leveraging Indigenous epistemologies like the Medicine Wheel and Two-Eyed Seeing to provide a richer, multi-dimensional approach to problem-solving and system design.
- Making AI Human-Centric: Crafting tools that generate not just outputs, but meaningful narratives, fostering deeper understanding and more ethical interactions.
Dive into the heart of the AvaLangStack with our specialized libraries, each designed to empower your LLM applications:
- Prompt Decomposition: Transform unstructured prompts into structured, actionable plans using Four Directions analysis.
- Inquiry Routing: Convert decomposed intents into routable inquiries, classified by Medicine Wheel direction and channeled to relevant knowledge sources.
- Relational Intelligence: Implement Indigenous relational paradigms with Medicine Wheel ontological filtering, importance tracking, value gating, and Fire Keeper coordination.
- Narrative Tracing: Gain deep, human-readable insights into your agents’ journeys with Langfuse-based narrative observability and cross-system correlation.
- State Machine Spec: Define declarative workflow specifications with formal validation, relational accountability mapping, and Mermaid visualization.
Deep Dive into Design: RISE Specifications
For a profound understanding of the architectural intent and creative orientation behind each package, explore our RISE (Reverse Engineering, Intent, Specifications, Exportation) Specifications. These documents articulate the “why” and “how” of the AvaLangStack’s design, grounded in our core principles.
Complementary Ecosystem: AvaLangGraph.js
The AvaLangStack is designed to integrate seamlessly with AvaLangGraph.js, a powerful framework for building complex agentic workflows and controllable StateGraph pipelines. Together, these two pillars form a comprehensive ecosystem for developing truly intelligent and relationally aware AI.
Getting Started
Ready to infuse your LLM applications with narrative and relational intelligence? Follow our Getting Started Guide to set up your environment and begin your journey with AvaLangStack.