1
Run an AgentFlow deployment
Choose a deployment model: SaaS, BYOC, in-VPC, or on-premises and private cloud. See Deployment models.
2
Configure authentication
Use the e6data session and SSO path, or the standalone JWT path. You can also enable personal access tokens for machine access and session exchange.
3
Enable at least one model
Turn on a model in the Model Registry. Supported providers are Anthropic, OpenAI, Amazon Bedrock, OpenRouter, and OpenAI-compatible proxy endpoints. See Models.
4
Make an e6data cluster available
AgentFlow needs an active e6data cluster to build semantic layers and run SQL. See Query Engine clusters.
5
Configure durable storage and Redis
Durable storage holds workflows, skills, history and audit records. Redis coordinates live work. See Architecture.
6
Turn on optional features you need
Uploads, external Cube, Slack, GitHub, GreptimeDB, MCP, enrichers, actions, triggers and response contracts are each enabled separately.
Next
Ask your first question
Create a project and a semantic layer, then chat with your data.
Deployment models
Pick where AgentFlow runs.