Skip to main content

Documentation Index

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

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

Gateway CLI provides commands for starting, monitoring, and managing the PraisonAI Gateway server and its daemon service.

​
Quick Start

Important: praisonai gateway start runs in the foreground. The daemon is installed by praisonai gateway install (or automatically by praisonai onboard).
1

Start Gateway

praisonai gateway start
2

Check Status

praisonai gateway status
3

Test Health Endpoint

curl http://127.0.0.1:8765/health

​
Commands

​
Gateway Management

CommandDescriptionExample
praisonai gateway startStart the gateway server (foreground)praisonai gateway start --port 9000
praisonai gateway statusCheck gateway and daemon statuspraisonai gateway status --daemon-only
praisonai gateway channelsList configured channelspraisonai gateway channels --json

​
Daemon Service

CommandDescriptionExample
praisonai gateway installInstall as OS daemonpraisonai gateway install --no-start
praisonai gateway uninstallRemove daemon servicepraisonai gateway uninstall
praisonai gateway logsShow daemon logspraisonai gateway logs -n 100
praisonai gateway restartRestart the daemonSee restart commands below

​
Testing & Debugging

CommandDescriptionExample
praisonai gateway sendSend test messagepraisonai gateway send --channel telegram --channel-id 12345 -m "test"

​
Command Reference

praisonai gateway start [OPTIONS]

Options:
  --host TEXT         Host to bind to [default: 127.0.0.1]
  --port INTEGER      Port to listen on [default: 8765]
  --agents TEXT       Path to agent configuration file
  --config TEXT       Path to gateway.yaml for multi-bot mode

Examples:
  praisonai gateway start
  praisonai gateway start --config gateway.yaml
  praisonai gateway start --agents agents.yaml --port 9000

​
Restart the Daemon

Use these OS-specific commands to restart the daemon service (same commands shown in the onboard Done panel): 
launchctl kickstart -k gui/$(id -u)/ai.praison.bot

​
Status Output Examples

​
Healthy Gateway

$ praisonai gateway status
Daemon service: Running (launchd)
Process ID: 12345
Gateway server: Reachable at http://127.0.0.1:8765/health
  Status: healthy
  Uptime: 3600.5 seconds
  Agents: 2
  Sessions: 1
  Clients: 3
  Channels: 2 configured

​
Daemon Issues

$ praisonai gateway status
Daemon service: Installed but not running (launchd)
Gateway not reachable at http://127.0.0.1:8765/health

​
Not Installed

$ praisonai gateway status --daemon-only
Daemon service: Not installed (systemd)

​
Platform Support

Gateway CLI works across platforms with native daemon integration:
PlatformService TypeLog LocationManagement
macOSLaunchAgent (ai.praison.bot)~/.praisonai/logs/bot-stderr.loglaunchctl kickstart -k gui/$(id -u)/ai.praison.bot
Linuxsystemd user service (praisonai-bot)journalctl --user -u praisonai-botsystemctl --user restart praisonai-bot
WindowsScheduled Task (PraisonAIGateway)Windows Event Logschtasks /End /TN PraisonAIGateway && schtasks /Run /TN PraisonAIGateway

​
Configuration Files

# Simple agent configuration
agent:
  name: "support"
  instructions: "You are a helpful support agent"
  model: "gpt-4o-mini"
  tools:
    - search_web
  memory: true

​
Best Practices

Use --daemon-only flag when monitoring daemon status in scripts or CI/CD pipelines to avoid gateway connection attempts.
Always check praisonai gateway logs when the daemon is running but gateway is unreachable - this reveals startup errors.
Use praisonai gateway send to test channel bot configuration before deploying to production environments.
Set up monitoring that runs praisonai gateway status --daemon-only to detect service failures quickly.

Gateway Server

Gateway architecture and configuration

Troubleshooting

Common gateway issues and solutions