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
mage0535/hermes-memory-installer
Hermes Memory Installer implements an agent-agnostic memory sidecar designed to provide persistent, multi-session memory and enhanced recall capabilities for various AI coding agents. It operates as a separate process, allowing it to integrate with agents like Hermes, Claude Code, or Cursor without requiring modifications to their internal codebases. The system archives agent sessions into a permanent knowledge base, enabling long-term memory across restarts. It employs a three-tiered retrieval architecture: a 'Hot Layer' for immediate context, a 'Warm Layer' utilizing PostgreSQL for extracted facts and recurring patterns, and a 'Cold Layer' based on 'gbrain' (a knowledge graph) and FTS5 for permanent archives and knowledge graphing. The sidecar also supports 'Focused Dossiers' for high-priority memory profiles, allowing specific entities like key people or projects to receive preferential treatment in recall. Users can select an embedding model for semantic search during installation, enhancing the system's ability to understand meaning and handle cross-lingual queries. The project provides an installer script and a suite of Python scripts for archiving, rebuilding indexes, monitoring capacity, and orchestrating the memory maintenance cycle. While it leverages general-purpose databases like PostgreSQL, its core functionality is specifically built to address the unique memory and recall challenges of AI agents.
https://github.com/mage0535/hermes-memory-installer
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.