AI SDK
The layer most TypeScript AI apps sit on: one call shape across twenty-odd model providers
What is AI SDK?
Four functions carry most of the work — generateText and streamText for prose, generateObject and streamObject for data shaped by a schema — and they keep the same signature whether the model behind them is OpenAI, Anthropic, Google, Bedrock or a local one. A second half supplies framework hooks so a streaming chat UI is a few lines rather than a hand-rolled parser. It is a model-access and UI layer, not an agent runtime: persistent memory, retrieval and durable orchestration are somebody else's job.
What can you do with AI SDK?
- Call any provider the same way — generateText and streamText take a model object and a prompt. Swapping OpenAI for Anthropic, Google, xAI, Azure, Bedrock, Groq, Mistral or DeepSeek changes that one object and nothing else in the call.
- Ask for data instead of prose — generateObject and streamObject take a schema and return a value that matches it, so extracting fields from a document or filling a form does not need a parser or a retry loop around malformed output.
- Give the model tools — The tool helper pairs a description with a schema and an execute function, and the SDK runs the resulting calls in a loop whose stopping condition you control rather than leaving the loop implicit.
- Stream into a UI without writing the plumbing — Framework-agnostic hooks cover React and Next.js, Vue and Nuxt, Svelte and SvelteKit, Expo and TanStack Start, handling the message list, the in-flight state and the token stream.
- Run an established agent harness through one API — A separate surface exposes existing agent harnesses behind a uniform interface, so a coding-agent style loop can be driven from the same codebase as the plain model calls.
Before you choose AI SDK
- This is the layer that talks to models, not the layer that runs agents; long-term memory, retrieval and durable multi-step execution have to come from elsewhere in the stack.
Star history
21 Aug to 28 Aug · +136
Frequently asked questions
Is AI SDK free for commercial use?
AI SDK is released under the Apache-2.0 licence — OSI-approved open source, which permits commercial use.
How can AI SDK be deployed?
AI SDK is available as Self-hosted / Runs locally.
Documentation
Reproduced from the vercel/ai README, published under UNKNOWN — read the LICENSE file. Read the original ↗
packages/ai/README.md
Other options in Agent Frameworks
deepseek-harnessFrameworks`dsh` is the agent harness DeepSeek AI develops itself. `npx @deepseek-ai/dsh web` brings up a Web UI on `http://127.0.0.1:3080`, and the architecture behind it is one where everything is a plugin, powered by the Cordis runtime, so it suits people who intend to extend a harness rather than only operate one. The caveat comes from the project itself: it is labelled a developer preview and warns in capitals that there will be compatibility-breaking changes, so plugins written today should budget for rework. It is also a poor fit if you want a documented scripted or embedded entry point right now, since the README covers only the `web` command and a source checkout, and links out to a development guide and architecture documentation without saying what either contains.
AutoGPTWorkflowAn agent here is a graph of blocks — one block calls a service, transforms data, prompts a model or branches — assembled on a canvas rather than written in code, then run on demand, on a schedule or from a trigger. One repository holds both the free self-hosted platform and the code behind the paid hosted one, and that is the catch: everything under the platform directory is PolyForm Shield, which permits use but forbids offering it as a competing product.
DifyWorkflowA complete platform — prompt orchestration, retrieval, agent tools and an admin UI — that non-engineers can operate once a team has set it up. The licence is a modified Apache 2.0 with additional conditions on multi-tenant hosting and branding, so it is source-available rather than open source. Read it before building a product on top.