Skip to main content
PraisonAIUI runs standalone or integrated with the PraisonAI wrapper using optional backend injection.
The user installs packages, launches praisonai dashboard --aiui, and interacts with the agent in the browser.

Quick Start

1

Install

2

Run integrated mode

Pattern B — In-process host

CLI:
Wires PraisonAISessionDataStore, PraisonAIProvider, and L1 bridges before create_app().

Pattern C — Gateway + static SPA

Or AIUIGateway.start() from praisonaiui.integration (calls the same bootstrap).

Legacy rollback

Set PRAISONAI_HOST_LEGACY=1 to skip provider wiring and use callback-only @aiui.reply handlers.

Backend injection

The wrapper calls praisonaiui.backends.set_backend() for hooks, workflows, usage, and approvals. Standalone aiui uses SDK defaults when no backend is injected. See also: backend-integration in the praisonaiui repo.

Best Practices

Pattern B (in-process host) is simpler to deploy and works well for most use cases.
Pattern C (Gateway + static SPA) scales better and enables independent UI and backend deployments.
Always configure allowed_origins when deploying to non-localhost to prevent unauthorized access.
Run praisonai onboard for guided setup — it handles credentials, ports, and daemon configuration.

PraisonAIUI

Frontend UI for PraisonAI agents

Gateway

Gateway configuration and setup