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.

​
AgentScheduler

Defined in the Agent Scheduler module.
AI Agents Framework Scheduler for running PraisonAI agents periodically. Features:
  • Interval-based scheduling (hourly, daily, custom)
  • Thread-safe operation
  • Automatic retry on failure
  • Execution logging and monitoring
  • Graceful shutdown

​
Constructor

​
agent
Any
required
The PraisonAI agent or AsyncPraisonAgentExecutor instance to run.
​
task
str
required
The prompt / task string passed to the agent on each run.
​
config
Optional[Dict[str, Any]]
Optional extra config (reserved; currently unused).
​
on_success
Optional[Callable[[Any], None]]
Invoked with the agent’s result after a successful run. Sync or async; exceptions are logged, not raised.
​
on_failure
Optional[Callable[[Exception], None]]
Invoked with the last captured exception after max_retries attempts fail. Sync or async; exceptions are logged, not raised.

​
Methods

start()

Start scheduled agent execution.

stop()

Stop the scheduler gracefully.

get_stats()

Get execution statistics.

execute_once()

Execute agent immediately (one-time execution).

​
Usage

scheduler = AgentScheduler(agent, task="Check news")
    scheduler.start(schedule_expr="hourly", max_retries=3)
    # Agent runs every hour automatically
    scheduler.stop()  # Stop when needed

​
Source

View on GitHub

praisonai/agent_scheduler.py at line 119

Agents Concept

Single Agent Guide

Multi-Agent Guide

Agent Configuration

Auto Agents