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
doobidoo/mcp-memory-service
MCP Memory Service is an open-source memory backend that gives AI agents and assistants long-term recall across sessions and across agents. It runs as a single self-hosted process and exposes the same store through several transports: the Model Context Protocol for MCP hosts, a plain HTTP REST API for pipelines built on LangGraph, CrewAI or AutoGen, a command line client, and a web dashboard. Memories are written as typed records with tags and metadata, embedded for semantic retrieval, and linked into a knowledge graph whose edges carry explicit relationship types, so an agent can follow causal chains between stored facts instead of only ranking isolated snippets. A consolidation process runs over the store to merge duplicates, decay stale entries and promote recurring facts, which keeps recall useful as the corpus grows. Retrieval combines vector similarity with tag and time filters and is reported in the single-digit millisecond range for typical local stores. Several storage backends are supported, including embedded SQLite with vector extensions and external vector databases, so the service can run entirely on a laptop or be shared by a team. Authentication covers OAuth 2.0 with dynamic client registration alongside simple API keys, which lets remote MCP clients connect over the network. The project ships Docker images, a PyPI package and setup guides for common agent frameworks and editors. It targets teams that want agent memory as shared infrastructure they operate themselves, rather than a hosted memory API or a pile of glue code around Redis and a managed vector store.
https://github.com/doobidoo/mcp-memory-service
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.