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
getmetal/motorhead
Motorhead is a specialized server designed to handle memory and information retrieval for Large Language Models (LLMs), simplifying the development of chat applications. It offers a compact API for managing conversation history, enabling LLMs to maintain context over longer interactions. The server stores messages for individual sessions, automatically triggers incremental summarization when a predefined window size is reached, and facilitates retrieval through vector similarity search (VSS) using Redisearch. This allows LLM applications to leverage past conversations and external knowledge for more coherent and informed responses. The project provides three core API endpoints: `GET /sessions/:id/memory` to retrieve conversation messages and context, `POST /sessions/:id/memory` to store new messages and optionally provide external context, and `DELETE /sessions/:id/memory` to clear session history. Additionally, `POST /sessions/:id/retrieval` enables semantic search against the session's memory, segmented automatically by session ID. Motorhead supports configuration options for window size, long-term memory (via Redisearch VSS), the LLM used for summarization, and API keys for OpenAI or Azure. While the project is currently marked as deprecated, its architecture demonstrates a common pattern for managing LLM state and retrieval in production.
https://github.com/getmetal/motorhead
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.