Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.cognee.ai/llms.txt

Use this file to discover all available pages before exploring further.

Cognee Cloud provides the full Cognee platform as a hosted service. It handles infrastructure, storage, and compute so you can focus on building knowledge graphs and querying them.

​
What Cognee Cloud provides

  • Managed infrastructure — Preconfigured compute, storage (PostgreSQL, LanceDB, Kuzu), and pipeline execution. No local installation required.
  • Pipeline execution — Run remember, recall, forget, and the lower-level add, cognify, search operations from the UI or API.
  • Web UI — Upload data, explore knowledge graphs, run searches, and manage datasets through the browser.
  • Python SDK — The cognee package connects to Cognee Cloud via cognee.serve(), using the same API as local Cognee.
  • Agent connections — Connect agent frameworks, local instances, or external data sources. See Connections.
  • Multi-tenancy — Dataset-level isolation with role-based access control. See Permissions.

​
Relationship to Cognee OSS

Cognee Cloud uses the same concepts, operations, and API patterns as open-source Cognee. The difference is deployment:
  • Cognee Cloud — Hosted persistence, managed compute, collaboration features.
  • Open-source Cognee — Local development, custom infrastructure, air-gapped environments.
You can connect a local Cognee instance to Cognee Cloud using cognee.serve().

​
Get started

Create an account

Sign up, start a free trial, and generate an API key.

Quick start

Upload data, build a knowledge graph, and run your first search.

Navigating the UI

Learn what each page in the Cognee Cloud console does.

Cloud functionality

Explore the API endpoints available in Cognee Cloud.

Connections

Connect agents, databases, or a local instance.

Architecture

How Modal compute, storage services, and datasets fit together.