SurrealDB integrates with popular AI and data frameworks, so you can use features such as vector search, graph relationships, and structured data storage from within them. These integrations help you build applications that combine LLMs, agents, data pipelines and more, using tools and frameworks you already know.
Integration | Description |
|---|---|
Agno | Agno is a python framework for building multi-agent systems with shared memory, knowledge and reasoning. |
Camel | A Python framework for building multi-agent LLM systems with SurrealDB vector storage capabilities. |
CocoIndex | An incremental indexing framework for AI agents with declarative SurrealDB table, relation, and vector targets. |
CrewAI | A framework for orchestrating role-playing AI agents with SurrealDB for entity and short-term memory. |
Dagster | A data orchestration framework with SurrealDB vector search integration for ML pipelines. |
Google Agent | A framework for building and deploying intelligent agents in Google Cloud with SurrealDB vector storage for RAG. |
Hermes | Nous Research's terminal agent, given a persistent filesystem in SurrealDB as a toolset and as a memory provider. |
Kreuzberg | A polyglot document intelligence framework to extract text, metadata, images, and structured information from documents (PDFs,images, etc.). |
LangChain | A framework for building LLM based applications. |
Llama Index | A framework for building RAG pipelines with SurrealDB's native HNSW vector index as the backing store. |
Mastra | A TypeScript agent framework with SurrealDB as a storage backend for conversation memory, workflow snapshots, and vector search. |
Pydantic AI | A Python framework designed to help you quickly, confidently, and painlessly build production grade applications and workflows with Generative AI. |
Smol Agents | A complete walkthrough for building a code-generating AI agent that recommends grocery items by querying SurrealDB's HNSW vector index. |