What is an agent loop?

The agent loop is the cycle an agent repeats: call the model, run the tools it asks for, feed the results back, and continue until it has an answer or hits a limit.

Open source

How AgentOven does it

Agents with agentic behavior run this loop in the Executor until the model returns a final answer or max_turns is reached (10 by default, configurable per agent). Recipe steps can loop as well, with a loop condition and a maximum number of iterations.

max_turnsAgentic behaviorLoop conditions
All 14 features →
Agent harnessContext engineeringMemory & sessionsTool calling & MCPMulti-agent orchestrationHuman-in-the-loopGuardrailsEvals & test suitesRL environments & worldsModel routingAgent observabilityAGENTS.md & GitOpsBackground agents