3. Why now?
The foundation models are ready.
The tools are maturing.
But the glue that connects everything is still missing.
LLMs are evolving fast—like, literally every week. New standards pop up (looking at you, MCP), and APIs change faster than you can keep track. The result?
Most AI agent projects never make it to production.
Those that do require constant maintenance and lack the reliability users expect. (new LLMs every week)
AI agents should be composable, reliable, and production-ready from day one. (minute one?) 2. What problem are we solving?
Every company is trying to build AI agents, but the infrastructure is missing. Takes too long. It's too expensive. Hire MLEs?
Teams are reinventing the wheel, building brittle systems that break in production + can't scale with their needs. Chai removes all the complexity of:
• LLM orchestration (unified API)
• Tool integration (deployment and scale)
• Memory (long term memory Auto RAG)
• Deploy agents, and scale to millions
• Langbase processes 100M+/mo agent runs With Chai, what used to take days/weeks — now only takes minutes.
From idea → agent → deployed!!
We wanted to make it super easy for everyone to building their AI agents.
People spend weeks wiring together LLMs, tools, and memory systems just to get something basic working. 1. Why are we doing this?
Everyone is building an AI agent today, but it's hard.
Cursor, perplexity, v0, chai, lovable, bolt — what do they all have in common?
They weren’t built on AI frameworks—they're built using primitives optimized for speed, scale, and flexibility. Chai is built on AI primitives by Langbase:
• Agents - for reasoning and planning
• Tools - for taking actions in the world
• Memory - for human-like context & learning
• Workflows - for orchestrating complex tasks
All with type safety and production reliability. Chai vibe coded a mini Perplexity for me 🤯
Unbelievably good. Can't wait to see what y'all will build. Our beta testers had multiple 🤯🤯🤯 moments.
Let's go! 👊 Vibe coded a Receipt OCR Agent
Give this agent a receipt image and it can analyze whatever you want in it.
Woohoo! 🥳🥳🥳 Watch me vibe code several AI agents in this video
- An AI agent to chat with pdf
- Agent that finds a lunch spot near me
- Bed time story maker agent by DT
- AI email agent that can summarize, analyze, and generate a response
Chai is beta right now, oh it's super powerful. For the first time, you can vibe-code any AI agent.
Meet Chai.new — Computer Human AI by Langbase ☕
🔹Prompt: "make an agent that…"
🔹Sip: chai builds any AI agent
🔹Ship: every agent gets a UI 🤯
Like your on-demand AI Engineer.
What will you s(h)ip today? 
Join here
discord.gg/mRsaj8FWTD
4:30pm LDN
11:30am NYC
8:30am SF Tomorrow we're hosting an open visitor hours on our discord. Join if you'd like to test out our new arrows, chat with the team, and maybe get a tour of our office.
Our new API Settings screen is designed for intuitive control over your API configurations. Adjust default bytes, prefixes, and manage security settings seamlessly. Less friction, more innovation
⚡️ Large schemas don't need to slow down your editor any more!
🔥 In 6.7.0, we improved our new `prisma-client` generator: Instead of a single file, it now outputs the generated code in smaller, logical chunks.
👉 Learn more in the 6.7.0 release notes: pris.ly/release/6.7.0 
Ready to try it? Check our docs to get started:
directus.io/docs/guides... Visual Editing has arrived! 🎉
Edit your website content directly where it lives:
👉 Click any element on your site and edit it instantly
👉 Browse your entire website within Directus
👉 See changes immediately as you make them
Content teams rejoice - your workflow just got a whole lot smoother. 
👋 Stop by our booth at @cloudnativegeo.org to say hi to our team, see a demo of our platform, and pick up some stickers! #CNG2025 
this guy reads construction physics…
Swift Stories has released its 8th edition. This issue explores building momentum through software, features insights from Elvira Burchik, a software creator and entrepreneur based in Berlin, and includes some resources curated from the Internet.
tuist.dev/newsletter/... 🤯 Yesterday, we released the first version of Prisma ORM without Rust engines!
This version provides a much better DX and also is:
🪶 More lightweight
🏎️ Faster (thanks to less serialization overhead)
✨ Easier to deploy (no more "binary targets")
pris.ly/no-rust-eng... 
We published a CVE for a moderate security vulnerability in vite's dev server. Only denied files in the project's root and apps using --host are affected. Please update to the latest versions: 6.3.4, 6.2.7, 6.1.6, 5.4.19, 4.5.14
github.com/vitejs/vite/... so does Skylight post to blusky and took your followers on here? I don’t usually mix my short form with socials and let it live in its own ecosystem
Vitess 22 is here!
This release comes with significant enhancements to query serving and cluster management. We've also improved performance in several key areas.
Get all the details on our blog:
planetscale.com/blog/announc...