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
Corpus-OS/corpusos
Corpus OS is an open-source protocol suite and SDK designed to standardize and bring interoperability to the backend infrastructure used by AI/ML applications, agents, and RAG pipelines. It addresses the complexity developers face when integrating multiple LLM, embedding, vector, and graph backends, each with unique APIs, error schemes, and rate limits. By offering stable, runtime-checkable protocols across these four domains, Corpus OS aims to reduce vendor lock-in and operational complexity associated with inconsistent monitoring and debugging across various services. The project introduces a normalized error taxonomy with retry hints and machine-actionable scopes, as well as SIEM-safe metrics for consistent observability. Its wire-first design means canonical JSON envelopes can be implemented in any language, with the provided Python SDK serving as a reference. Corpus OS is not a replacement for higher-level AI frameworks like LangChain or LlamaIndex; instead, it aims to standardize the infrastructure layer _underneath_ them, allowing application teams to retain their preferred frameworks while platform teams benefit from a unified protocol, error taxonomy, and observability model across all AI traffic. This enables seamless swapping of providers or frameworks without extensive re-integration work, fosters easier adoption for backend vendors through a conformance suite, and provides platform and infra teams with unified dashboards and SLOs.
https://github.com/Corpus-OS/corpusos
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.