Google has introduced Middleware for Genkit, its open-source framework for building AI-powered and agentic applications. The update adds a programmable interception layer around model calls, tool execution, and generation loops, giving developers more control over reliability, safety, and orchestration inside production AI systems.
The release enhances Genkit by enabling developers to inject custom behaviors into workflows. Middleware can now add features like retries, model fallbacks, and logging without changing application logic. Genkit supports TypeScript, Go, and Dart, with Python support coming soon.
According to Google, every generate()
call in Genkit operates through a tool loop in which the model generates output, executes tools, processes results, and continues until completion. Middleware hooks can intercept that cycle at three levels: generation, model calls, and tool execution.
Google also released several prebuilt middleware components. These include retry handling with exponential backoff, automatic fallback to alternative models when APIs fail, approval gates for sensitive tool calls, filesystem access controls, and a “skills” system that dynamically injects instructions from local files.
The company said middleware components can also be stacked together, allowing retries, filters, approvals, and logging to operate in a defined execution order. The system is also integrated into the Genkit Developer UI, where developers can inspect middleware behavior, trace execution flows, and debug runtime interactions.
The release reflects a broader trend across the AI tooling ecosystem toward operational safeguards and runtime controls for autonomous systems. Instead of relying only on prompts or model tuning, frameworks are increasingly adding programmable layers that govern how models behave during execution.
The announcement prompted discussion around how Genkit fits into Google’s broader AI tooling ecosystem. Developers on X debated the distinction between Genkit and Google’s Agent Development Kit (ADK).
In response, Michael Doyle, a software engineer at Google, clarified the distinction between the two frameworks:
Have an app (web, mobile, etc)? Want to add agentic features to it? Use Genkit! Building complex, standalone, multi-agent systems? E.g. on GCPs Agent Platform? Use ADK.
The exchange highlighted how Google is positioning Genkit primarily as an application-layer framework for integrating AI features into existing products, while ADK targets larger orchestration-heavy agent systems running on dedicated infrastructure.
Google said developers can begin using the middleware system immediately through the latest Genkit release and publish custom middleware packages for reuse across projects.