Open source. Open possibilities.

CocoIndex is an open-source incremental indexing framework designed to provide AI agents and LLM applications with continuously fresh context by reprocessing only changed data.

TalaDB is an embedded vector and document database designed for on-device AI, providing a unified TypeScript API across Browser, Node.js, and React Native.

DB-GPT is an open-source agentic AI data assistant that connects to databases, spreadsheets and knowledge bases, autonomously writes SQL and Python code, runs reusable skills in sandboxed environments, and turns analysis into charts, dashboards and reports.

HelixDB is an OLTP graph-vector database built in Rust on object storage, designed for knowledge graphs and AI memory.

LightRAG is a lightweight graph-based retrieval-augmented generation framework from HKUDS, offering dual-level retrieval, knowledge-graph indexing, multimodal parsing, multiple storage backends and an API server with WebUI.

An all-in-one AI framework for semantic search, LLM orchestration, and language model workflows.

SYNAPSE is an AI-powered intelligence aggregation and automation platform featuring a multi-agent system and RAG capabilities for research and document generation.

Deep Lake is a serverless multimodal database for AI that combines vector search with storage for embeddings, images, video, audio, and documents. It streams data directly from cloud storage to PyTorch/TensorFlow, supports versioning, and integrates with LangChain, LlamaIndex, and Weights & Biases.

PageIndex is a vectorless, reasoning-based RAG engine that builds hierarchical tree indexes for long documents and lets an LLM reason through the tree to retrieve relevant sections, avoiding vector databases and chunking.

Python SDK for the AskNews API that injects real-time news context into any LLM with a single line of code, offering endpoints for news search, event tracking, forecasting, analytics, deep research, knowledge graphs, and web search.

LEANN is a lightweight vector database designed for personal RAG applications, reducing storage requirements by up to 97% through graph-based selective recomputation.

PixelRAG renders documents as screenshots and retrieves over images directly, preserving visual structure like tables and charts that text parsing loses. Includes a hosted 8.28M-page Wikipedia index, CLI tools, and Claude Code integration.