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
CaviraOSS/LongMemory
LongMemory, published earlier as OpenMemory, is a self-hosted memory engine for large language models and AI agents. It targets the problem of stateless models: instead of replaying an ever-growing transcript, an application writes facts and events into LongMemory and asks it for the relevant slice at answer time. The project positions itself as a cognitive memory layer rather than a vector store, combining embeddings with structured recall so that a lookup returns not only matching text but an explainable trace of why an item was recalled. The engine is local-first and stores its data in SQLite or Postgres, so a deployment needs no managed service. Two client libraries are published, openmemory-py for Python and openmemory-js for Node, and both expose the same basic surface: add a memory, query for context, and inspect the recall trace. Integrations are provided for LangChain, CrewAI, AutoGen, Streamlit, the Model Context Protocol and a VS Code extension, which lets desktop assistants and coding agents share one memory backend. Beyond application-written memories, LongMemory can ingest from external sources including GitHub, Notion, Google Drive, OneDrive and a web crawler, turning documents already held elsewhere into retrievable context. The maintainers note that the project is being rewritten and that breaking changes should be expected. It fits teams building assistants, chat products or multi-agent systems that need cross-session continuity without operating a separate vector database and retrieval pipeline. Because the store runs on the same machine as the application, it also suits privacy-sensitive deployments where conversation history must not leave local infrastructure.
https://github.com/CaviraOSS/LongMemory
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.