Multi Llm Backend Support

via “multi-provider llm integration with configurable model selection and fallback”

Universal memory layer for AI Agents

Unique: Uses factory pattern (LlmFactory) to abstract 18+ LLM providers behind a unified interface, enabling zero-code provider switching and fallback logic. Supports both cloud APIs (OpenAI, Anthropic) and local/self-hosted models (Ollama, vLLM) with identical configuration.

vs others: More flexible than LangChain's LLM abstraction because it includes fallback logic and supports more providers, and more practical than building provider-specific integrations because it centralizes provider management in a single factory class.