Skip to main content
The praisonai flow command launches Langflow with PraisonAI components pre-loaded, and provides YAML ↔ Langflow JSON conversion utilities.

​
Quick Start

1

Install

pip install "praisonai[flow]"
2

Launch

praisonai flow
3

Build visually

Open http://localhost:7860 and drag Agent / Agent Team components from the PraisonAI sidebar.

​
How It Works

PhaseDescription
Installpip install "praisonai[flow]" pulls Langflow and requests
LaunchCLI sets LANGFLOW_COMPONENTS_PATH to PraisonAI components
BuildDrag Agent and Agent Team nodes in the browser
Exportpraisonai flow export <flow_id> converts back to YAML

​
Subcommands

​
praisonai flow

Start the visual builder.
FlagTypeDefaultDescription
--port, -pint7860Port to listen on
--host, -Hstr127.0.0.1Host to bind to (use 0.0.0.0 to expose)
--env-filestrNonePath to a .env file Langflow should load
--no-openflagFalseDon’t open the browser on start
--log-level, -lstrerrordebug, info, warning, error, critical
--backend-onlyflagFalseRun backend API only (no frontend UI)
--components-pathstrNoneExtra custom components directory (appended to PraisonAI’s)
praisonai flow --host 0.0.0.0 --port 8080

​
praisonai flow import

Convert PraisonAI YAML → Langflow JSON and upload.
FlagTypeDefaultDescription
yaml_pathstr—Path to YAML workflow file (positional)
--urlstrhttp://localhost:7860Langflow server URL
--dry-runflagFalsePreview JSON without uploading
--openflagFalseOpen the imported flow in the browser
--output, -ostrNoneSave JSON to file instead of uploading
praisonai flow import my_workflow.yaml --open

​
praisonai flow export

Download a Langflow flow and convert back to YAML or JSON.
FlagTypeDefaultDescription
flow_idstr—Flow ID to export (positional)
--output, -ostr<flow_name>.<ext>Output file path
--urlstrhttp://localhost:7860Langflow server URL
--formatstryamlOutput format: yaml or json
praisonai flow export abc-123-def -o my_workflow.yaml

​
praisonai flow list

List flows on a running Langflow server.
FlagTypeDefaultDescription
--urlstrhttp://localhost:7860Langflow server URL
--search, -sstrNoneSearch flows by name or description
praisonai flow list --search research

​
praisonai flow version

Show installed Langflow version. 
praisonai flow version

​
Common Patterns

# YAML → visual editor round-trip
praisonai flow                                   # 1. start the builder
praisonai flow import my_workflow.yaml --open    # 2. push YAML in
# (edit in browser, copy the flow ID from the URL)
praisonai flow export <flow_id> -o my_workflow.yaml   # 3. pull edits back to YAML

# Preview the converted JSON without uploading
praisonai flow import my_workflow.yaml --dry-run

# Run on a custom port / expose to LAN
praisonai flow --host 0.0.0.0 --port 8080

# Headless / API-only deploy
praisonai flow --backend-only --no-open

​
Best Practices

Always export back to YAML for version control after visual edits.
Preview JSON conversion with praisonai flow import workflow.yaml --dry-run before pushing to a running server.
Extend the sidebar with your own Langflow components via --components-path /path/to/components.
Skip the UI in CI or Docker with praisonai flow --backend-only --no-open.

Visual Workflow Builder

UI guide for Agent and Agent Team nodes

Langflow Integration

Component reference and model formats

Dashboard

Unified dashboard — launches Flow + Claw + UI together

Installation Extras

[flow] extra reference