{"slug": "why-client-sdk-generation-belongs-in-the-open", "title": "Why client SDK generation belongs in the open", "summary": "Google and Speakeasy have open sourced Speakeasy's OpenAPI code generation suite under the AGPLv3 license, following the abrupt shutdown of Google's previous SDK generation provider in May 2026. The partnership migrated Google's GenAI SDKs for the Interactions, Agents, and Webhooks APIs in place, and the resulting pipeline now powers six client targets (three released SDKs) with roughly one engineer to maintain, down from multiple engineers for handcrafted generators. The AGPLv3 license lets developers run the generator in development or CI pipelines while keeping ownership of generated code under licenses such as MIT or Apache 2.0.", "body_md": "Over the last few months, we worked closely with Speakeasy to ship the new [Google GenAI SDKs](https://ai.google.dev/gemini-api/docs/libraries) for our [Interactions](https://ai.google.dev/api/interactions-api), [Agents](https://ai.google.dev/api/agents), and [Webhooks](https://ai.google.dev/api/webhooks) APIs. Today, we're excited to announce that we’ve partnered with Speakeasy to make their OpenAPI code generation suite [open source](https://github.com/speakeasy-api/openapi-generation).\n\n``` python\nfrom google import genai\n\nclient = genai.Client()\n\ninteraction = client.interactions.create(\n    model=\"gemini-3.8-flash\",\n    input=\"Analyze this commit log and find regressions.\",\n)\n\nprint(interaction.output_text)\n```\n\nGenerating clean, idiomatic SDKs across multiple languages from rapidly evolving OpenAPI specs is an engineering challenge. For years, the frontier AI ecosystem, including Google, relied on specialized tooling to generate client libraries that could handle complex streaming protocols, strict error hierarchies, and rich type unions without feeling machine-generated.\n\nIn May 2026, right as we were gearing up for Google I/O and the General Availability of the [Interactions API](https://ai.google.dev/gemini-api/docs/interactions-overview), the SDK generation provider we were using was acquired and abruptly announced its shutdown.\n\nThis sudden disruption highlighted that proprietary, closed-source generators create unacceptable platform risk. If the industry relies on OpenAPI to define interfaces, the tooling to compile those interfaces into client libraries, CLIs, and agent tools should be open infrastructure.\n\nAs we were reworking our SDK pipeline on a tight timeline, our top priority was minimizing developer disruption and avoiding breaking changes.\n\nWe partnered with Speakeasy to migrate our client libraries in place, with the core commitment to make the generator suite open source. The migration required careful engineering: aligning type definitions across all target languages, preserving strict error hierarchies and streaming behavior, and integrating the generator directly into our internal monorepo and build system.\n\nAt Google DeepMind, while we use AI across our development workflows, we believe in choosing the right tool for each layer of the stack. Transforming formal API specifications into multi-language SDKs demands determinism and strict type safety. With Speakeasy, we pair a fast, deterministic generator at the core with Antigravity AI agents accelerating the custom parts of the SDK.\n\nMaintaining previously handcrafted generators used to take multiple engineers. Today, this setup powers our client pipeline across six targets (three released SDKs, with more rolling out shortly) with roughly one engineer to maintain.\n\nTo help ensure the broader developer ecosystem has access to high-quality, well-maintained SDK generation tooling without the risk of similar disruptions, [Speakeasy is open sourcing](https://www.speakeasy.com/blog/partnering-with-google) its full OpenAPI client suite under the AGPLv3 license.\n\nThe generator is licensed under AGPLv3. This allows you to run it in your development or CI pipeline while keeping complete ownership of your generated code/SDKs under your chosen license (such as MIT or Apache 2.0). If you modify the generator compiler itself, the AGPL guarantees those improvements remain open to the community.\n\nYou can explore the new [Gemini Interactions API](https://ai.google.dev/gemini-api/docs/interactions-overview) today using our updated SDKs. If you want to generate your own client libraries, CLIs, or MCP servers, you can find the Speakeasy generator on [GitHub](https://github.com/speakeasy-api/openapi-generation) and run it against your OpenAPI specs.\n\nThanks for reading! Keep on building.", "url": "https://wpnews.pro/news/why-client-sdk-generation-belongs-in-the-open", "canonical_source": "https://developers.googleblog.com/why-client-sdk-generation-belongs-in-the-open/", "published_at": "2026-09-17 19:24:44.371322+00:00", "updated_at": "2026-09-17 19:24:45.753749+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "developer-tools", "ai-agents", "agent-protocols"], "entities": ["Google", "Speakeasy", "Google DeepMind", "Google GenAI SDKs", "Interactions API", "Agents API", "Webhooks API", "Antigravity"], "alternates": {"html": "https://wpnews.pro/news/why-client-sdk-generation-belongs-in-the-open", "markdown": "https://wpnews.pro/news/why-client-sdk-generation-belongs-in-the-open.md", "text": "https://wpnews.pro/news/why-client-sdk-generation-belongs-in-the-open.txt", "jsonld": "https://wpnews.pro/news/why-client-sdk-generation-belongs-in-the-open.jsonld"}}