Comparisons / Flue vs Vercel AI SDK
Flue vs Vercel AI SDK: Which Agent Framework to Use?
Flue vs Vercel AI SDK, head to head
Flue and Vercel AI SDK both let you build an agent, but they sit in different parts of the stack and they assume different things about who's writing the code.
Flue is a declarative TypeScript agent framework from Fred K.
The Vercel AI SDK is a TypeScript-first toolkit for building LLM apps.
Underneath, both wrap the same thing: a model call, a tool dispatch, a loop. The decision is about which abstraction your team wants to think in day to day, and which ecosystem you're willing to inherit along with it. There's an honest, framework-free version of the same pattern in about 60 lines of Python in the lesson at the bottom of this page — useful as a baseline regardless of which framework wins.
Pick Flue if
Pick Flue if flue is the natural choice when the deploy target is Cloudflare and you want a TypeScript-first, declarative agent framework tuned for Durable Objects. Its cross-runtime story (Cloudflare + Node + CI) is genuinely useful if agents run in more than one place. For a single-agent loop that doesn't need persistence, plain TypeScript is simpler. The tradeoffs in its intro should match how your team already thinks about agents; Vercel AI SDK will feel like translation if they don't.
Pick Vercel AI SDK if
Pick Vercel AI SDK if vercel AI SDK is the right pick for TypeScript apps where the LLM is one piece of a bigger React app — you get streaming primitives, provider-portable tool calling, and useChat hooks all in one package. For a server-side agent or a learning exercise, the plain fetch version is simpler and shows you what's happening on the wire. The tradeoffs in its intro should match how your team already thinks about agents; Flue will feel like translation if they don't.
By the numbers
By the numbers
Flue
2.4k
140
TypeScript
MIT
2026-05-01
Fred K. Schott + Astro team (at Cloudflare)
Cloudflare
Cloudflare Durable Objects; also deploys to Node, GitHub Actions, GitLab CI
Yes
Vercel AI SDK
16.8k
2.7k
TypeScript
Apache-2.0
2023-06-13
Vercel
Vercel (public)
2.4M
Works on any host; tightly integrated with Vercel deploy + AI Gateway
Yes
Used by: v0.dev, Cursor, Sourcegraph
github.com/vercel/ai→GitHub stats as of April 2026. Stars indicate community interest, not necessarily quality or fit for your use case.
| Concept | Flue | Vercel AI SDK |
|---|---|---|
| Agent | `createAgent({ model, instructions, tools })` — declarative config, framework runs the loop | `generateText({ model, tools, maxSteps })` runs the loop and returns final text |
| Tools | Registered with valibot schemas: `{ name, description, schema, execute }` | `tool({ description, parameters: z.object(...), execute })` |
| State | Durable Streams — replayable, checkpointed event log stored in Cloudflare Durable Objects | — |
| Deployment | One config controls deploys to Cloudflare, Node, GitHub Actions, or GitLab CI | — |
| Runtime | The Pi harness — same runtime as OpenClaw, so agents share tooling with that ecosystem | — |
| Cloudflare-native | Durable Objects give per-agent persistence and locking without an external DB | — |
| Streaming | — | `streamText` returns a `ReadableStream` of deltas with built-in parsing |
| Structured output | — | `generateObject({ schema })` returns parsed/validated objects |
| UI hook | — | `useChat()` returns `{ messages, input, handleSubmit, isLoading }` |
| Provider swap | — | Change one import: `openai('gpt-4o')` → `anthropic('claude-3-5-sonnet')` |
Or build your own in 60 lines
Both Flue and Vercel AI SDK implement the same 8 patterns. An agent is a function. Tools are a dict. The loop is a while loop. The whole thing composes in ~60 lines of Python.
No framework. No dependencies. No opinions. Just the code.
Build it from scratch →