AI SDK
An open-source AI development toolkit released by Vercel. It provides a unified API for calling a variety of AI models and supports features such as streaming responses and tool calling, simplifying the development of AI applications.
Core Facts
@ai-sdk/provider-utils is responsible for the general-purpose utility functions in the AI SDK for interacting with model providers, including low-level logic such as streaming response parsing, tool call formatting, and error handling.
@ai-sdk/provider defines the standard interface, @ai-sdk/provider-utils provides common utility functions, and each specific vendor package implements its own adapter logic
@ai-sdk/xai is the adapter-layer provider package in the AI SDK targeting the xAI Grok series of models.
Timeline (last 90 days)
When using a virtual model, simply replace the original provider model ID with `vmc/<slug>` (such as `vmc/coding-agent`) in AI SDK or compatible API requests to invoke it.
The AI Gateway interface is compatible with the AI SDK as well as OpenAI- and Anthropic-compatible APIs, allowing teams to change the underlying provider without rewriting calling code.
Provider options refer to request parameters specific to each provider (such as Anthropic's extended thinking budget or OpenAI's reasoning effort), which are passed in the AI SDK through a separate providerOptions field and cannot be used across providers.
The AI SDK's tool ecosystem is continuing to be refined, and the wrapping of basic tools such as bash has entered a maintenance iteration phase, with the related capabilities becoming mature.
The AI SDK repository typically uses tools such as changesets to manage versions and changelogs: developers submit change descriptions, and the release workflow aggregates them and then automatically calculates version numbers, generates the changelog, creates git tags, and pushes to npm.
In the AI SDK's modular architecture, UI-layer components (such as TUI) typically depend on the abstract interfaces, streaming response handling, or message protocol definitions provided by the core ai package.
`@ai-sdk/tool-web-fetch` is an officially provided preset tool package that wraps web fetching into a standard Tool interface, so developers can mount it for model use without implementing the fetching logic and parameter validation themselves.
@ai-sdk/workflow-harness released version 1.0.167, a patch-level release (Patch Changes) automatically built and signed by the github-actions bot, corresponding to commit a5db0af.
The old fx adapter required installing fx inside the sandbox, running the sandbox bridge, and exposing sandbox ports for external communication.
The fx adapter of HarnessAgent in AI SDK underwent an architecture-level refactor: harness and model requests no longer run in the sandbox but run in the same process as the application.
40 more timeline events
All Facts (20)
@ai-sdk/provider-utils is responsible for the general-purpose utility functions in the AI SDK for interacting with model providers, including low-level logic such as streaming response parsing, tool call formatting, and error handling.
90%Verified@ai-sdk/provider defines the standard interface, @ai-sdk/provider-utils provides common utility functions, and each specific vendor package implements its own adapter logic
90%Verified@ai-sdk/xai is the adapter-layer provider package in the AI SDK targeting the xAI Grok series of models.
90%Verified@ai-sdk/vue is the adapter layer for the Vercel AI SDK within the Vue ecosystem.
90%VerifiedThe AI SDK splits out independent adapter layers for different frontend frameworks, including corresponding packages for Vue, React, Svelte, and other frameworks.
90%Verified@ai-sdk/voyage is the official provider package within the Vercel AI SDK dedicated to Voyage AI embedding models
90%VerifiedVercel AI SDK provides a unified abstract interface, so switching model service providers typically only requires replacing the Provider configuration without rewriting business logic.
90%Verified@ai-sdk/tui is the TUI (Terminal User Interface) module in the Vercel AI SDK, extending AI SDK capabilities to command-line terminal environments.
90%VerifiedIn AI SDK, workflow-harness serves as the runtime scaffold responsible for orchestrating and executing AI workflows, linking multiple AI calls, tool calls, state management, and other steps into a controllable workflow.
90%Verified@ai-sdk/zai is the official Provider in the Vercel AI SDK for Zhipu AI models.
90%VerifiedThe AI SDK adopts a Provider architecture in which each Provider package implements standardized interfaces such as LanguageModelV1, which is an engineering practice of the strategy pattern.
90%VerifiedVercel AI SDK is an open-source toolkit led by Vercel that provides a standardized large language model integration solution for JavaScript/TypeScript developers.
90%VerifiedVercel AI SDK provides unified abstract interfaces (such as generateText and streamText), allowing developers to maintain a consistent coding style when calling different model providers.
90%VerifiedThe Vercel AI SDK adopts a Monorepo single-repository management model, with the core package ai and various framework adapter packages (such as @ai-sdk/vue, @ai-sdk/react, and @ai-sdk/svelte) released in coordination.
90%Verified@ai-sdk/workflow is a sub-package within the Vercel AI SDK ecosystem focused on workflow orchestration
90%VerifiedFor projects that use multiple @ai-sdk/* packages simultaneously, keeping their versions synchronized during upgrades helps avoid potential compatibility issues.
85%Verified@ai-sdk/provider-utils is a companion utility library containing common logic such as stream parsing, error handling, and request retrying.
85%Verified@ai-sdk/valibot is a Valibot integration module provided by the Vercel AI SDK, allowing developers to use Valibot to define data structures and integrate them into the AI SDK's generation pipeline.
85%VerifiedThe AI SDK uses a monorepo single-repository management pattern, where changes to the underlying harness package are followed by patch-version updates to the upper-layer workflow-harness package.
85%VerifiedVercel AI SDK adopts a framework-agnostic design approach, providing dedicated binding packages for mainstream frontend frameworks such as React, Vue, Svelte, and SolidJS.
85%