Build every step of agents on one platform

Ship production-ready agents faster and more reliably across your products and organization.

TL;DR

AgentKit allows for faster and more reliable production-ready agent development.
Offers a 70% reduction in iteration cycles and 40% faster agent evaluation.
Provides visual (Agent Builder) and code-first (Agents SDK) development options.
Includes built-in tools such as web search, file search, image generation, and code interpreter.
Features deployment via ChatKit and optimization through Evals for testing and refinement.
Agent accuracy can be increased by up to 30% with evaluations.

Continue reading the original article

Addy Osmani reposted

Andrej Karpathy

Wow, this tweet went very viral!

I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the other person's agent customizes & builds it for your specific needs.

So here's the idea in a gist format: https://t.co/NlAfEJjtJV

You can give this to your agent and it can build you your own LLM wiki and guide you on how to use it etc. It's intentionally kept a little bit abstract/vague because there are so many directions to take this in. And ofc, people can adjust the idea or contribute their own in the Discussion which is cool.

Satya Nadella

Great example of what Foundry enables: durable, stateful agents that run across time boundaries, orchestrate tools and models, and close the loop with evaluation and improvement over long-running workflows. @jeffhollan https://t.co/v0yWTDIcn3

Elon Musk reposted

X Freeze

Grok Imagine Agent Mode (Beta) just went live on Grok web

It’s a full creative agent working on one infinite open canvas

Grok Agent plans → generates → edits → iterates everything automatically in the same workspace

Tell it what you want and watch it plan, generate, edit, and iterate everything in one seamless workspace:

• 🎬 “Generate a 1-minute cinematic film”

• 📚 “Create a complete manga set”

• 🛍️ “Build UGC product stories”

This is the real leap from simple prompts to end-to-end creative production

This is the biggest upgrade to Grok Imagine yet

Elon Musk

Try the Grok Imagine agent mode beta!

Addy Osmani reposted

fks

Introducing Flue — The First Agent Harness Framework

Flue is a TypeScript framework for building the next generation of agents, designed around a built-in agent harness.

Flue is like Claude Code, but 100% headless and programmable. There's no baked in assumption like requiring a human operator to function. No TUI. No GUI. Just TypeScript.

But using Flue feels like using Claude Code. The agents you build act autonomously to solve problems and complete tasks. They require very little code to run. Most of the "logic" lives in Markdown: skills and context and AGENTS.md.

Flue is like Astro or Next.js for agents (not surprising, given my background 🙃). It's not another AI SDK. It's a proper runtime-agnostic framework. Write once, build, and deploy your agents anywhere (Node.js, Cloudflare, GitHub Actions, GitLab CI/CD, etc).

We originally built Flue to power AI workflows inside of the Astro GitHub repo. But then @_bgiori got his hands on it, and we realized that every agent needs a framework like Flue, not just us.

Check it out! It's early, but I'm curious to hear what people think. Are agents ready for their library -> framework moment?

Addy Osmani

Software engineers before vs. after agents :)

If this is you: try Cloud agents (they're pretty good!) or at least Amphetamine to keep your Mac from sleeping when the lid is closed.

Yann LeCun reposted

NYU Center for Data Science

AI agents often struggle to plan movements because their internal representations of the physical world can be overly tangled.

CDS PhD student Ying Wang (@yingwww_) shows how straightening these pathways improves AI navigation.

Accepted to ICML 2026.

https://t.co/BOJCXWwWS8

Aravind Srinivas reposted

Perplexity

We've published our internal manual for building agent skills.

Skills require a new way of thinking for developers.

https://t.co/Rw88kBYXqR

Aravind Srinivas

A research blog on how Perplexity builds agents and agent skills for products like Computer.

Satya Nadella reposted

Jeff Hollan

Here's another reason why @Microsoft Foundry is the BEST platform in the world to build and run your agents: Our durable, long running agents come with Toolbox 🔨

Toolbox allowed me to reduce input tokens 90%(!!) and significantly simplify the amount of code needed

Check out the demo below and see how you can bring hundreds of tools through a single MCP endpoint -- all running in Foundry at cloud scale! ☁️

Elon Musk

Try it out!

Elon Musk reposted

tetsuo

40 Grok Build agents tearing through C code in parallel. All supervised by DAD.

DAD is a lightweight autonomous tmux supervisor for long-running Grok tasks. Built entirely in Grok Build.

/dad "your objective" launches grok --yolo (the Son) and spins up two loops:

2-min fast loop: nudges only when the Son is stuck, frozen, finished, or waiting. Hands off in Plan mode.

12-min deep loop: re-reads the objective, pushes back if the Son lowers the bar, triggers /compact at ~50% context.

Re-attachable. Walk back to a DAD-* window hours later and Dad rehydrates the loops.

Set and forget. Dad watches, the Son works.