Step 1 — Connect your data
Choose a data source on the left or upload files directly on the right. Upload files- Drag files into the drop zone, or click to browse. Supported formats: PDF, CSV, TXT, Markdown, JSON, DOCX.
- Alternatively, paste text content directly.
- Local Cognee — Sync a running local instance. See Syncing a Local Instance.
- Agent — Connect an agent framework. See Connecting an Agent.
- Database — Ingest from PostgreSQL, MySQL, Slack, Notion, and others. See External Data Sources.
Step 2 — Build memory
Cognee processes your data automatically:- Upload — Files are stored in your dataset.
- Extract entities — Named entities and concepts are identified.
- Build knowledge graph — Relationships between entities are created and embeddings are generated.
cognify operation. Processing time depends on the volume of data.
Step 3 — Search your data
Enter a natural language query, or select a suggestion. Cognee searches the knowledge graph you just built and returns contextual results. This uses graph-backed search — the same mechanism asrecall and search.
Step 4 — Done
Your knowledge graph is built and searchable. From here you can:- Go to the Dashboard for an overview of your workspace
- Open Datasets to manage your data
- Connect an agent to use Cognee as memory
You can skip the onboarding at any point and return to it later. All progress is preserved.
Next steps
Dashboard
Overview of your workspace, stats, and quick actions.
Cloud functionality
Explore the full API surface available in Cognee Cloud.