# AI SDK Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/ai-sdk
> Markdown URL: https://aitinkerers.org/technologies/ai-sdk.md
> Technology record last updated: 2026-03-09T12:29:32Z
> Generated: 2026-09-21T16:44:38Z

The AI SDK is Vercel's open-source, TypeScript toolkit: it provides a unified API for building AI applications across major web frameworks (React, Vue, Svelte) and over a dozen model providers.

This is the definitive TypeScript toolkit for AI application development, created by Vercel and the Next.js team. It abstracts away the complexity of integrating Large Language Models (LLMs) from providers like OpenAI, Google Generative AI, and Anthropic, allowing you to switch models by changing a single line of code. The SDK includes two main libraries: AI SDK Core for unified API calls (streamText, generateObject) and AI SDK UI for framework-agnostic hooks (useChat) to build rich, generative user interfaces fast. With over 2 million weekly downloads, it’s a proven solution for deploying robust, multi-provider AI apps on the web.

- Official technology site: https://ai-sdk.dev
- Public AI Tinkerers demos and talks: 3
- Result page: 1 of 1

## Recent Public Talks and Demos

### [LLM Is Now the Drone Pilot. What Could Go Wrong?](https://london.aitinkerers.org/talks/rsvp_8EiI2q4KMuQ)

We’ve all asked an LLM to write an email, draft some code, or summarize a meeting. But what if we gave it the controls to something a bit more… kinetic? Like, say, a drone. What could possibly go wrong? In this talk, we’ll explore the rise of autonomous AI agents through the lens of everyone’s favorite nightmare scenario: the chatbot that can actually move things in the real world. We’ll laugh (and maybe wince) our way through examples of unexpected agent behavior, the thin line between “smart assistant” and “chaotic intern,” and the real risks of turning text prediction into real-world action. By the end, you’ll know both why autonomous agents are so exciting—and why you might want to keep them very far away from your flying lawnmower.

- Event context: AI Tinkerers x MongoDB - Demopalooza — 2025-10-07 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_8EiI2q4KMuQ

### [An API Client, a Database Client, and an AI Walk Into a Workspace…](https://austin.aitinkerers.org/talks/rsvp_MIqcR-tZaHY)

This isn't the GenAI demo you're looking for. But it's exactly what you want: prompt, instant working endpoint! A Postman-on-steroids, a live SQL editor, and a pocket LLM in a single pane. 1. Design and instantly mock endpoints with the look and feel of an API Client with AI assistance 2. Write a SQL query using the query tool with AI assistance 3. Attach the query results to your API endpoint with a single click Just your usual lateral thinking with withered technology demo.

- Event context: Community AI Demos – Austin • July 10 2025 — 2025-07-10 — Austin
- Public talk page: https://austin.aitinkerers.org/talks/rsvp_MIqcR-tZaHY

### [Copilot as Controller](https://seattle.aitinkerers.org/talks/rsvp_LGWeYT9gm6E)

What’s possible when you make your AI engine in charge of all of your business logic? It turns out it can think creatively about solutions that you might not have thought of. This demo is of a copilot architecture I’m calling multi-brain - a kind of mixture of experts that can run complex planning and development tasks by generating requirements and ensuring the implementation conforms to them by noticing conflicts and suggesting changes. All UI inputs are sent to the copilot and all changes to the data model are made by the copilot, allowing for generative UI and non-web app interfaces like slack or phone. I’ll demo it using Zucca.ai - PSL’s soon to be latest spin out. Architecture details- Demo will be creating the requirements, formula, manufacturing process, equipment list, labor plan, and calculate cogs for a 100,000 unit run of a new food product designed on the spot. Takes about 2 minutes. Then I’ll go over the components: - Copilot AI engine that sits between UI and data model - Engine is made of a master control router that decides what parts of the expert system to call - On-the-fly brain building from partials - use of code interpreter to write code to run unit economics analysis and COGS - labeled code blocks used to stream UI elements using - undo-stack built-in because all changes are tied to messages

- Event context: AI Tinkerers Seattle - December 2024 Meetup — 2024-12-12 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_LGWeYT9gm6E

## Related Technologies

- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Agents SDK](https://aitinkerers.org/technologies/agents-sdk) ([Markdown](https://aitinkerers.org/technologies/agents-sdk.md)) — 2 public demos
- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 public demos
- [Code Interpreter](https://aitinkerers.org/technologies/code-interpreter) ([Markdown](https://aitinkerers.org/technologies/code-interpreter.md)) — 2 public demos
- [Moondream](https://aitinkerers.org/technologies/moondream) ([Markdown](https://aitinkerers.org/technologies/moondream.md)) — 7 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 99 public demos
- [Slack](https://aitinkerers.org/technologies/slack) ([Markdown](https://aitinkerers.org/technologies/slack.md)) — 15 public demos
- [Zucca](https://aitinkerers.org/technologies/zucca) ([Markdown](https://aitinkerers.org/technologies/zucca.md)) — 1 public demo