The APIMatic CLI can now build a context plugin from your published SDKs and hand you the commands that publish it to GitHub. Two new commands do the work: apimatic plugin generate and apimatic plugin publish.
Previously, in order for an API provider to use Context Plugins for their API, their SDKs had to be published to a public package manager such as npm, NuGet, or PyPI. That left teams whose SDKs live behind a private host — internal APIs, partner integrations, or APIs that aren't yet ready for public distribution — without a way to offer the same AI-assisted integration experience.
We've now added self-hosted SDK support in Context Plugins. Instead of pulling the SDK from a package manager, the AI agent downloads the SDK package from your portal, installs it locally in the developer's workspace, and wires it into their project — all without the SDK ever needing to be published.
Developers increasingly don't read API documentation page by page — they build with AI coding tools like Claude Code, Cursor, and VS Code. And these tools are only as good as the context they have. Without accurate, current knowledge of your API, they guess: invented endpoints, stale parameters, and integration code that takes hours to hand-fix.
We've brought your API into that workflow. Right from your developer portal, developers can now load your full API context — docs, SDKs, code samples, and setup instructions — into their AI coding environments in a single step, using Context Plugins.
Our SDKs are now more AI ready than ever. Model reference docs now show idiomatic, language-specific code samples, complete with imports, instead of serialized payloads. They cover how to initialize a structure, reference an enum value, and catch errors across all seven SDK languages.
We've improved llms.txt and llms-full.txt for developer portals and added per-page Markdown exports. These updates make the documentation easier for AI tools to read and help them return answers that are more accurate, relevant, and grounded in the same content users see in the portal.
We've introduced a new OpenAPI linting ruleset for Agentic Tools generation.
We've extended LLM context generation to include Webhooks and Callbacks documentation. Both llms.txt and llms-full.txt now provide AI tools like ChatGPT and Claude with comprehensive information about your event-based API interactions.
We’re excited to announce support for generating llms.txt and llms-full.txt files as part of your developer portal. It enables tools like Cursor, GitHub Copilot, ChatGPT, and Claude to quickly understand your documentation.