ToolOpenAI

OpenAI launches Agents v2 framework with multi-model orchestration

Native support for Claude and Gemini alongside GPT-5, improved state management.

April 19, 20265 min readPublished byOpenAI

OpenAI published version 2 of its open-source Agents framework yesterday, with a major change: native support for competing models, notably Anthropic's Claude and Google's Gemini. Developers can now orchestrate multi-agent workflows where each agent uses the model best suited to its task.

v2 also introduces a more robust persistent state management system, based on pluggable stores (Redis, Postgres, or custom solution), and a new observability API that allows tracing each model call and routing decision. The framework remains under MIT license and installs via pip.

This repositioning is strategic: by making its framework model-agnostic, OpenAI implicitly acknowledges that the agents market won't be monopolized by a single provider and seeks to establish itself as the standard orchestration layer, even at the cost of letting competitors benefit from the traffic.

Tags
openaiagentsframeworkmulti-model