Today we're releasing a new set of components for building chat interfaces.
We've taken the patterns we build every day, rethought the abstractions behind them, and turned them into components you can compose and customize.
We're starting with the conversation layer: streaming, scrolling, messages, bubbles, attachments, and markers.
Hmm, not sure I like this "fullscreen" non-flicker version of @ClaudeDevs. Triggering answer selection on mouse clicks feels like bad UX for a terminal interface.
Agent frameworks are becoming the JavaScript frameworks of AI. New ones every week, endless abstractions, and they all promise to be the silver bullet.
Data API Client v2.4 is out, and it now has a Prisma adapter for the Amazon RDS Data API!
That rounds out the set. @Prisma, @DrizzleORM, @kysely_, and @kibertoad's Knex all work with Aurora Provisioned and Serverless v2, Postgres and MySQL.
https://t.co/6Dh5umP9jO
Just spent the last two weeks reworking my local Agent Hub system to use @opencode as the harness with qwen, gemma4, and mistral local models. Then I get this at 7:01pm. ๐
Knex.js now runs on the @awscloud Aurora Serverless Data API.
data-api-client v2.3.0 adds a Knex compat layer for Postgres and MySQL. Transactions, joins, CTEs, upserts, the whole query builder. @DrizzleORM and @kysely_ too. No connections to manage.
https://t.co/eEFIeaHVhv
For the last couple of years, we've been focused on giving AI systems access to information through better models, larger context windows, and RAG.
But memory is what separates systems that answer questions from systems that actually learn.
As agents and agentic workflows move into production, memory is becoming a first-class architectural concern. The question isn't just what information is stored. It's how that knowledge is accumulated, organized, retrieved, and applied over time.
I've been collaborating with the @OracleDatabase Developer Relations team on a series of articles and demos exploring stateful AI architectures. My first post on the Oracle Developer Blog was published yesterday and explores the evolution from RAG to memory systems, along with practical implementation patterns and a companion demo.
New in Ampt CLI v1.2.0: `ampt reset` wipes your sandbox data, storage, and cached modules so you get a clean environment in seconds. Works on preview environments too with `share --reset`. Same URL, fresh state. Great companion for AI coding agents.
https://t.co/Njd4Yf28Mp
went through this Claude Sub cancellation thread from Theo
500+ replies, ~70% actual cancellations = 350 people gone (can actually be higher than this)
rough math (assumptions):
- 210 Pro @ $20 = $4,200/mo
- 84 Max $100 = $8,400/mo
- 56 Max $200 = $11,200/mo
$23,800/month. $285K/year. From one tweet.
and this is just the people who replied ๐