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
verygoodplugins/automem
AutoMem is an AI memory service designed to provide robust, long-term memory capabilities for AI assistants, addressing limitations of traditional RAG and vector databases. It utilizes a dual-storage architecture, combining FalkorDB, a graph database, for storing memories as nodes with 11 typed relationships, and Qdrant, a vector database, for storing embeddings of each memory. This hybrid approach enables a sophisticated recall mechanism that incorporates semantic similarity, graph traversal, temporal alignment, tag overlap, and importance scoring. The service emphasizes multi-hop bridge discovery, allowing AI assistants to identify causal relationships, preferences, and underlying principles by traversing the stored graph. It supports 11 authorable relationship types (e.g., RELATES_TO, LEADS_TO, PREFERS_OVER) and automatically adds others via an enrichment pipeline. Inspired by neuroscience, AutoMem also includes memory consolidation cycles (Decay, Creative, Cluster, Forget) to manage relevance, discover non-obvious connections, and group similar memories, ensuring the memory adapts and strengthens over time. It is designed for self-hosting with Docker or Railway, targeting solo developers, prosumers, and small teams who require ownership of their memory data. The project builds upon peer-reviewed memory research from institutions like Ohio State and DeepMind, implementing techniques from papers such as HippoRAG 2 and A-MEM.
https://github.com/verygoodplugins/automem
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.