The toolbox

Framework for building LLM applications, with abstractions for chains, retrieval, agents and integrations.

Best for: Composing LLM pipelines

Data framework for connecting private documents and databases to language models for retrieval and agents.

Best for: Retrieval over your own data

Managed vector database for similarity search over embeddings, with hybrid search and metadata filtering.

Best for: Managed vector search

Open-source vector database written in Rust, available self-hosted or as a managed cloud service.

Best for: Self-hosted vector search

API that crawls websites and returns clean markdown or structured data suitable for LLM input.

Best for: Turning web pages into context

Open-source observability platform for LLM applications, covering tracing, evaluation and prompt management.

Best for: Tracing and evaluating LLM apps