Skip to content

Agno 3.1.11 puts Claude and Codex harnesses inside teams

Updated Agno

Summary

Harness agents can join teams and workflow steps, while new session-search endpoints support nested filters.

Tool
Agno
Category
Frameworks
Date
Pricing
Not stated in the sources we cited.

Agno released 3.1.11 on October 27, 2026. Its main addition is orchestration across agent harnesses, rather than a new underlying model.

Harness agents become workflow members

ClaudeAgent and CodexAgent can now participate in teams and workflows, including parallel, conditional and looping steps. Each keeps its own model, tools, workspace and conversation across turns. A configured sandbox gives a harness member its own container for a turn.

Search and manage ongoing work

New session-search endpoints support nested AND, OR and NOT filters before pagination. Company tasks gain more flexible stage changes, while routines gain cancellation, archive and restore operations.

These are documented capabilities, not measured performance gains. Using a harness or model still requires the relevant access and infrastructure; orchestration support does not provide free model inference.

See the agno hub.

More from Agno

View all

Questions

What is Agno?

According to its documentation, Agno helps companies run agents as a service. You build agents with the Agno SDK, Claude Agent SDK, Codex SDK or another supported framework. Agno then runs them as a service with durable execution and multi-replica scaling, exposed through a REST API and an MCP server.

Is Agno open source?

The GitHub API reports the Apache-2.0 license for the agno-agi/agno repository. The cited sources do not give pricing for any hosted offering.

Does Agno support MCP?

Yes. The documentation says Agno exposes agents through a REST API and an MCP server, which lets you make a product available in AI apps such as Claude and ChatGPT. The docs can also be given to coding agents through MCP.

Filed on Agent Radar. Claims in this note are limited to the sources above.