Did you know you could Iframe Noteable's outputs, including our DEX's interactive visualization. Bridge the gap between Data science and Data Analytics, in a matter of seconds.

We’ve also published the notebooks to Noteable, so you can run them online without any setup from a link. Expect to see more coming quickly - we’re really excited to bring more examples like this to the JS community 🤲

Excited to announce our new open source project: Pixeltable – a declarative data infra for multimodal AI apps. Store, transform, index, and iterate on your data through an intuitive table interface. Less compute, less code, more insights, and no more redundant processing.

Build an AI RPG Adventure App in 30 minutes. - Define your character, e.g. Elon Musk - Choose Your Genre, e.g. Cyberpunk - Define a starting Scenario, e.g. You're the CEO of Neural Link Industries in Austin, 2049... - Choose your next move 👇

Wordpress is dead. Vibe coded in 2 hours while multi-tasking with Cursor and Anthropic (Sonnet 3.7) this entirely functioning website with login/sign-up, input forms, blog, custom UI, animations... I didn't write one line of code.

After 1.5 days (still multitasking like crazy on many other stuff). Mostly hooked up to mock endpoints but people who have never built a B2B/C SaaS Product with such complex workflows do not understand how life-changing this is. Dumb stuff such as browse/search/sticky

Who said there were only 24 hours in a day?

Try in Carmel.

Matt Shumer Happy to chat. Long-term memory here in 20 lines of code, lazy evaluation, efficient caching/parallelization... all in the database: docs.pixeltable.com/docs/examples/… I've a couple of sample apps on Github where I'm using it already. An infinite-memory discord and multimodal local

What do you use for coding in Cursor, as of today?

Here is a step-by-step tutorial on building a complete stateful OpenAI agent. (If you know Python, this is all you need to learn to build a working agent in an hour, including complete explanations of every component.) This agent: • It's conversational • Has persistent

Santiago Pixelagent isn't just another agent framework. It's a collection of clear, concise examples demonstrating how to build robust, customizable agent functionality directly on top of Pixeltable's data infrastructure. I hope it inspires people to build their own agent class from

Santiago Thanks for the post Santiago. The updated location for this tutorial is: github.com/pixeltable/pix…

Lior⚡ We should find a more efficient way to configure LLMs other than wasting 24k tokens.

Aaron Levie Memory is simply storage, orchestration, retrieval and indexing. No need for fancy abstraction. You just need a multimodal data infrastructure: github.com/pixeltable/pix… What matters is the pre- and post-processing from the given “MCP” client to maintain that external memory

The Ultimate Python Library for Multimodal AI Meet Pixeltable—a unified, declarative framework that handles your entire multimodal pipeline, from data storage to model execution. Seamlessly manage images, videos, text, and tabular data—all in one place. 100% open-source.

jason liu I DM'd you my bank information.

If you want to help build the next-gen open source multimodal AI data infrastructure, DMs open. You'll work alongside people who built: F1/BigTable, parquet format, Impala, Yellowbrick, MapR, Dremio, SanDisk and built the ML platforms at Airbnb/Twitter (X), & Amazon.

Soham Parekh Good luck! You gonna need a Data Infra that actually handles videos/images/audio then! Pixeltable is built by the team who created parquet (the file format), Twitter, Amazon, and Airbnb ML Platforms... You'd be surprise how much we abstract data plumbing for you.

Pixeltable: AI Data Infrastructure Providing a Declarative, Incremental Approach for Multimodal Apps