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
DrDroidLab/open-index
Open Index builds what it calls a brain: a domain-specific, structured and searchable context graph that agents can operate on, and that stays correct as the underlying systems change. The model rests on four primitives. A doc_type names a concept worth tracking, such as service, customer or issue. A doc_schema declares the fields stored for that concept. An entity is one instance stored according to its schema, and every entity can link to others through a target reference plus free-text edge semantics that describe what the relationship means. A connector is an optional source that entities are extracted from, for example an MCP server, and connectors carry schedules so they can be re-run from cron or continuous integration to keep the graph current. The tool is domain-agnostic: the same primitives model a support organisation, a sales pipeline or an infrastructure inventory, because the concepts are declared rather than built in. A command line interface scaffolds a brain, adds doc types, validates and imports entities, rebuilds the search index, runs connectors, and searches from the terminal; validation is designed to run in continuous integration so malformed entities fail a build. An explorer user interface adds schema, exploration, relationship map, analytics and job views, and the graph can be served from a container with a shared database when several agents need the same brain. Because the store is structured and validated rather than a pile of embedded text, agents retrieve typed records and traverse explicit relationships instead of ranking loose chunks. It suits teams giving agents reliable domain grounding that survives changes in the source systems.
https://github.com/DrDroidLab/open-index
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.