Lars Grammel
banner
lgrammel.bsky.social
Lars Grammel
@lgrammel.bsky.social
My talk about AI SDK 5 from the AI Meetup in Wrocław is on youtube: www.youtube.com/watch?v=xgR-...
AI SDK 5: What’s New and What’s Next by Lars Grammel | AI Meetup in Wrocław, September 2025
YouTube video by Callstack
www.youtube.com
October 12, 2025 at 7:38 AM
prediction: as ai relies more and more on websearch, seo for ai will bring product placement and then it will be followed by ads for ai (content suggestions), esp. in free ai chatbot tiers. ai chatbots will become more like google search in some of those ways.
September 7, 2025 at 2:23 PM
I find this research fascinating because it means that there is a path towards smaller models that are strong on tool use and reasoning and that use external knowledge sources (through tools such as web search) instead of baked in knowledge.

openai.com/index/why-la...
September 7, 2025 at 2:16 PM
Reposted by Lars Grammel
The previously sensible advice to never use ChatGPT for search needs to be rethought - GPT-5 in thinking mode is shockingly good at running searches now simonwillison.net/2025/Sep/6/r...
GPT-5 Thinking in ChatGPT (aka Research Goblin) is shockingly good at search
“Don’t use chatbots as search engines” was great advice for several years... until it wasn’t. I wrote about how good OpenAI’s o3 was at using its Bing-backed search tool back …
simonwillison.net
September 6, 2025 at 7:44 PM
At React Universe Conference Wroclaw today - would love to chat with AI SDK users.

If you are around and want to give feedback or learn more about the AI SDK send me a DM.
September 3, 2025 at 9:43 AM
Finally - almost 5 months of work, our biggest release so far.

Completely revamped, type-safe AI chat is a game changer imo. I don't know any other framework that has full stack support for this. Hope it will enable you to build the next generation of AI applications.
AI SDK 5

Introducing type-safe chat, agentic loop controls, data parts, speech generation and transcription, Zod 4 support, global provider, and raw request access.
July 31, 2025 at 4:15 PM
You can try AI SDK 5 now:
AI SDK 5 Alpha (Early Preview)

An entirely new foundation with LanguageModelV2, a rearchitected useChat, new agentic controls and more.

Play with the alpha release and help us improve it.

Disclaimer: not yet ready for production use or migrating existing projects.
May 16, 2025 at 1:40 PM
AI SDK 5 prototype: custom UI data parts

You can define custom ui data parts and stream updates to them from the server:
May 14, 2025 at 5:44 PM
AI SDK 5 preview: ChatStore & ChatTransport

ChatStore synchronizes chat write operations and manages streaming state. You can use it directly or through framework integrations like useChat.

ChatTransport makes backend integrations more flexible, allowing for client-only usage.
May 13, 2025 at 3:05 PM
AI SDK 5 preview: UI message persistance

We recommend storing UI messages, not model messages, if your application has a useChat component.

This ensures that the UI state can be correctly restored and helps integrating backends other than streamText (e.g. Langchain).
May 11, 2025 at 12:26 PM
AI SDK 5 preview: UI message metadata

UI messages in AI SDK 5 will have a generic metadata property (instead of specific properties like createdAt).

This lets you send and show the message metadata that's important in your application:
May 10, 2025 at 4:53 PM
UI messages != model messages

What you display to the user (ui messages) is different from what you want to send to the LLM (model messages).

UI messages contain additional information such as custom app data and metadata. Tools calls might be omitted. etc.
May 10, 2025 at 4:52 PM
In AI SDK 5, UI messages will be composed of parts.

This is my current vision of how UI messages could look like - feedback welcome.
May 10, 2025 at 4:49 PM
Starting to be excited about AI SDK 5

Our planned timeline:

- alpha 1st half of May
- beta 2nd half of May
- GA in June
May 10, 2025 at 4:47 PM
AI agents vs workflow runs & run termination:

Workflows have a deterministic number of steps after which they will finish with with a solution (of varying quality).

Agents run in a loop and it is unclear when and if they will finish with a solution.
one fundamental issue w/ ai agents:

the problem of deciding when to stop an agent run is a variant of the halting problem

there will always be agent runs for which, given their current state and history, it cannot be known whether they will terminate with an answer or not
April 29, 2025 at 11:06 AM
one fundamental issue w/ ai agents:

the problem of deciding when to stop an agent run is a variant of the halting problem

there will always be agent runs for which, given their current state and history, it cannot be known whether they will terminate with an answer or not
April 27, 2025 at 6:58 AM
Combining the provider registry with custom providers and middleware is extremely powerful for setting up your models in one place:
March 26, 2025 at 5:48 PM
You can set custom headers, e.g. for auth, when using the MCP SSE transport:
Header support for MCP SSE transport
March 24, 2025 at 5:04 PM
Lots of new features shipped since January, check out our 4.2 release:
AI SDK 4.2

Introducing MCP clients, reasoning, sources and more.
March 21, 2025 at 10:34 AM
The AI SDK now supports LLMs that generate file outputs, first example are images:
March 19, 2025 at 1:24 PM
Reposted by Lars Grammel
lot of people asked for this, and while I can claim ~zero credit I'm very happy it's out there

really digging the class-based APIs (`chat = new Chat(...)` etc) that are popping up in the Svelte ecosystem. Classes are great! They feel solid, tangible. I missed them.
AI SDK Svelte 2.0 is here with native Svelte 5 support.

Thanks to Elliot and @rich-harris.dev for this huge update!
March 17, 2025 at 6:41 PM
Reposted by Lars Grammel
AI SDK Svelte 2.0 is here with native Svelte 5 support.

Thanks to Elliot and @rich-harris.dev for this huge update!
March 17, 2025 at 11:01 AM
Reposted by Lars Grammel
The AI SDK now supports the OpenAI Responses API:
March 11, 2025 at 5:48 PM
Sometimes you need to access provider-specific information from the responses that is not directly extracted by the AI SDK.

When you use generateText or generateObject, you can now access the full JSON response body and use additional data:
AI SDK 4.1.53

Access the full provider response when using generateText and generateObject
March 5, 2025 at 5:19 PM
Reposted by Lars Grammel
Send your own URL sources to the client:

bsky.app/profile/sdk....
February 20, 2025 at 12:48 PM