Posts tagged releases

Learn what 0.5 through 0.8 added around the agent: evals, tool permissions, sandboxes, delegation, typed memory, AG-UI clients and production builds.

Learn how the offline agent test added to the starter in 0.4 works, and what a scripted model response can verify.

Build your own agent.

Start a project, or follow the code-fixer agent from its first failing test to a verified patch.