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
kantord/SeaGOAT
SeaGOAT is a self-hosted, local-first semantic code search engine designed for the AI age. It allows users to search their codebases using natural language queries, leveraging vector embeddings generated locally. The tool does not rely on third-party APIs or remote servers for its core functionality, ensuring data privacy and offline usability. It employs ChromaDB as its vector database and a local vector embedding engine, complemented by ripgrep for traditional keyword and regular expression searches. The project provides a server component that can be run locally or self-hosted, enabling speedy responses by pre-processing codebase files into vector embeddings. This design allows for querying even while the processing is ongoing, offering immediate regular expression results and progressively more accurate semantic results. SeaGOAT supports a variety of programming languages and text file types, focusing on an incremental processing approach that avoids blocking user's computer resources. Key features include local operation, semantic search capabilities for code, integration with regular expressions, and configurable server settings. The project emphasizes ethical use by primarily functioning as a search engine rather than a code generator, thus not creating AI-derived work. While currently designed for local execution, the architecture allows for optional remote hosting for teams, with security considerations explicitly mentioned for private codebases.
https://github.com/kantord/SeaGOAT
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.