Kraci

Product Engineer @e2b / prev staff eng @productboard

daily focus @locu_app

[Kraci @_kraci]

📈

[Vasek Mlejnsky @mlejva]

Our weekly usage is now higher than was our whole usage in August and it keeps growing

[Kraci @_kraci]

e2B

[Vasek Mlejnsky @mlejva]

Should we start a Polymarket bet on when we hit 3B?

[Kraci @_kraci]

ClickUp Brain² × E2B

[E2B @e2b]

ClickUp’s Brain² runs every frontier model with full context of your company, writing and running code to build reports, decks, and dashboards across all teams.

That code touches sensitive workspace data, has to start instantly mid-conversation, and has to scale to millions of users. That’s why @ClickUp built its execution layer on E2B: every sandbox is its own microVM, starts from a prebuilt template with tools ready, and scales on demand.

Enterprise-ready, from SOC 2 to HIPAA to full isolation.

[E2B @e2b]

Waiting months for API access? Give Claude a computer instead.

Use E2B with @claudeai's new computer and browser use toolset, and Claude gets an isolated cloud machine where every action becomes a click or keystroke.

Use it to automate the work an API can't reach, like testing your own UI end to end or entering data into a legacy app.

Docs: https://t.co/ACZD3JY2Mr
Cookbook Example: https://t.co/QEeMBv0fNJ

[Kraci @_kraci]

Arena is my go-to tool for seeing which model works best for my job

[E2B @e2b]

Arena started in 2024 as a UC Berkeley Sky Computing Lab project for comparing models head to head. Today, it's grown into a platform for evaluating model performance across agents, text, code, images, and videos, running up to 600,000 @e2b sandboxes a day.

Each sandbox is an isolated cloud computer where an agent can write code, install dependencies, and work for hours on coding, research, reports, and presentations. That isolation keeps results trustworthy and secure: no session's code or files can reach another's and skew the comparison.

That security at scale gets tested every time a frontier model drops. Before GPT-5 went public, people rushed to Code Arena to try it first.

"When GPT-5 was about to come out, a lot of people came to Code Arena to experience the model firsthand because it wasn't out to the public yet. E2B was the backbone behind all of that. So when we had this massive surge, we didn't have to worry about whether we could handle it."

- Aryan Vichare, Founding Engineer, @arena

Read the full case study: https://t.co/aosIe1Leko

Watch the case study video:
https://t.co/EWlqrUpviG

[Kraci @_kraci]

E2B sandboxes, now on your own infrastructure.

[E2B @e2b]

Introducing E2B Embed: it brings AI agent sandboxes directly into your product and run them on infrastructure you control.

E2B Embed packages the full E2B stack on a single node, giving you the flexibility to deploy in your own environment or a customer’s. Open source under Apache 2.0, it supports Docker Compose, Terraform on GCP, and Kubernetes. All with the same E2B SDK, CLI, and API.

https://t.co/KQ0UsBouiM

[Vasek Mlejnsky @mlejva]

Yesterday, we had one of the most exciting visits in the @e2b office.

The @nvidia team delivered the devkit of their new Vera CPU. Vera is a new family of ARM-based CPUs made specifically for running agents and sandboxes.

Our initial benchmark tests show extremely promising numbers, pretty much unmatched across the industry. Turns out the company that makes killer GPUs also makes killer CPUs.

[E2B @e2b]

Why make an agent choose one way of solving a problem when it can explore them all?

Catch our very own @mishushakov and @ondrej_sh at @aiDotEngineer on Thursday, September 24, as they show how agents can fork live machines to explore multiple paths in parallel- each with its own copy of the machine’s state, filesystem, and running processes.

[Kraci @_kraci]

@Ignorebysweet @e2b 👀

[Kraci @_kraci]

@AdityaShips "One task. Your full attention."

How do you approach this in the AI era, when we’re often working on multiple tasks at the same time? What’s your approach?

[Kraci @_kraci]

@adilrc MX Master 4 has a separate thumb button for it

[Vasek Mlejnsky @mlejva]

We open-sourced our infra repository in the very early days of @e2b

Today we’re reintroducing it as E2B Runtime: the open-source execution layer for agents running on E2B.

[E2B @e2b]

🚀 Our open-source project has a new name: E2B Runtime.

Behind every E2B stack there's a runtime. Cloud, enterprise, or embedded in your product. Same code, Apache-2.0.

Old URL redirects. Something new is already in the tree. More soon.

https://t.co/W39mncwM9j

[Kraci @_kraci]

@charlieholtz The only reason I would consider buying the iPhone Duo is definitely agentic coding

[Vasek Mlejnsky @mlejva]

What we need is a smart orchestration. Matthew's take is correct. Agents don't always need a full sandbox (which should be a VM, not a container btw), but it's not the agent's job to figure that out. It's the job of the underlying infrastructure.

Frankly, given where we're headed, we shouldn't even be thinking in terms of one sandbox per agent. Agents will need their own private clouds.

This is one of the problems we're thinking about. If working on this interests you, you should reach out.

[Ondrej @ondrej_sh]

@dhh @Dell just made it run on @e2b, went for 8 cores 8 GB RAM and cruising < 10 % CPU lol

[Vasek Mlejnsky @mlejva]

Historically, E2B sandboxes have run on Firecracker microVMs. Today, we have a dedicated sandbox team made up of experts who have built Firecracker-like microVMs in the past, and we've taken that experience to build our own runtime.

We're now running a custom runtime with significant improvements on top of the general Firecracker architecture.

[Kraci @_kraci]

I’m joining @e2b as a Product Engineer.

Over the last year, I worked on Productboard Spark, an agentic system for product teams.

That gave me a much better understanding of what it takes for agents to move from impressive demos to real work.

It’s not just the chat interface.

It’s the environment around the agent: where it runs code, uses tools, accesses context, recovers from failure, and gives developers visibility into what actually happened.

That’s why I decided to join E2B.

I’ll be working on dashboard, observability, traceability, and developer experience for teams building agentic systems.

Looking forward to building this next layer with the E2B team.

[Kraci @_kraci]

The product harness for PMs is here. I’m grateful I got to be part of this journey from day one, and I’m excited to see it live now. Proud of what the team has shipped!

[Hubert Palan @hpalan]

Today the way product teams work changes forever.

Productboard Spark, the first agentic product system, is now generally available.

Here's why we rebuilt our entire product from the ground up 🧵