pathwaycom/llm-app
Ready-to-run cloud templates for building real-time RAG, AI pipelines, and enterprise search applications that synchronize with various live data sources.
Awesome Infra for AI › Vector Databases & Retrieval Infrastructure
divagr18/memlayer
Memlayer is designed to seamlessly integrate intelligent, persistent memory capabilities into large language models (LLMs) and AI agents with minimal code. Its core functionality revolves around enhancing LLMs' ability to recall context across conversations, extract structured knowledge, and proactively surface relevant information. The system uses a hybrid storage approach, combining a vector database (ChromaDB) for semantic similarity search with a knowledge graph (NetworkX) for entity relationships and structured facts, ensuring comprehensive memory management. Memlayer features an intelligent salience gate that uses ML-based classification or OpenAI embeddings API to filter and store only important information, skipping irrelevant conversational filler. This allows for efficient memory utilization and retrieval. It offers three operation modes—LOCAL, ONLINE, and LIGHTWEIGHT—catering to different performance, cost, and deployment needs, from fully offline high-volume production to serverless environments. Retrieval is optimized with three search tiers (Fast, Balanced, Deep) to meet varying latency requirements, combining vector search with optional knowledge graph traversal for complex queries. The framework supports major LLM providers like OpenAI, Claude, Gemini, and local models via Ollama or LMStudio, offering a consistent API for interchangeability. Memlayer's focus is squarely on operationalizing LLM memory, making agents more contextual and enabling sophisticated retrieval-augmented generation (RAG) paradigms without manual prompting. Advanced features include proactive task reminders based on stored memory.
https://github.com/divagr18/memlayer
Also in Vector Databases & Retrieval Infrastructure
run-llama/llama_index
LlamaIndex is an open-source data framework for building LLM applications by connecting custom data sources to large language models, focusing on data ingestion, indexing, and retrieval augmented g...
milvus-io/milvus
Milvus is a high-performance, cloud-native vector database designed for scalable vector Approximate Nearest Neighbor (ANN) search, efficiently organizing and searching vast amounts of unstructured ...
VectifyAI/PageIndex
PageIndex is a vectorless, reasoning-based RAG system that builds hierarchical tree indexes from documents and uses LLMs to reason over them for context-aware retrieval.
qdrant/qdrant
Qdrant is an open-source, high-performance vector similarity search engine and vector database designed specifically for AI applications, enabling fast storage, search, and management of vectors wi...
Tencent/WeKnora
WeKnora is an open-source, LLM-powered knowledge framework for enterprise document understanding, semantic retrieval, and autonomous reasoning, featuring RAG, ReAct agents, and an auto-maintaining ...
topoteretes/cognee
Cognee is an open-source AI memory platform that provides AI agents with persistent long-term memory through a self-hosted knowledge graph, combining vector embeddings and graph reasoning.
RyanCodrai/turbovec
TurboVec is a Rust-based approximate nearest neighbor (ANN) vector index with Python bindings, built on Google Research's TurboQuant algorithm for efficient, memory-optimized vector similarity search.