E2B

We have just launched the E2B deal for YC founders. 🫡 20 YCombinator startups are joining the first batch of the deal. We are proud to support companies like Rivet, Redouble, or Prox with use cases like: 🔸 LLMs safety benchmarks 🔸 Cursor-like coding assistants for accountants, biologists, and social scientists 🔸 AI that generates, tests, and deploys full-stack apps from natural language 🔸 User simulator environments for training collaborative AI agents 🔸 RL environments for evaluating dataset quality 🔸 Cybersecurity agents that run penetration tests in sandboxed containers. See the deal is live on Bookface. To check out other E2B startup programs, look for "E2B for Startups" on our web.

Full guide: e2b.dev/docs/use-cases…

Running a headless browser inside your agent sandbox is the default, but it can be brittle. Cold starts. CAPTCHAs. Auth state lost on restart. Proxies. Our new template built with friends @usekernel splits the loop. The agent runtime runs in the e2b sandbox. The browser runs on Kernel, which handles cold start, CAPTCHA, residential proxies, and session persistence across hours. Connect them over CDP. Three things you can build with it this weekend. → Screenshot app endpoints. Deploy a web app in a sandbox, screenshot every route. → Agent data extraction. Let an LLM autonomously browse and extract data. → Live browser preview. Watch the browser in real time via Kernel's live view. Try the guide today!

Learn more: e2b.dev/blog/not-affec…

Security won't affect 99% of your day-to-day with a sandbox provider. But the 1% outweighs the other 99% combined. CVE-2026-31431 is the 1%. Root on every Linux since 2017, cross-tenant on shared-kernel hosts. If your sandbox provider runs in containers, you should immediately check whether they're exposed to this. E2B isn't affected, by design. Here's why: Per-sandbox kernels. Every E2B sandbox runs in its own Firecracker microVM. Own kernel, own memory, own page cache. Bugcrowd's analysis of Copy Fail puts it cleanly: the boundaries that hold are the ones that don't share a kernel. A kernel exploit inside the sandbox cannot reach the host: the attacker would need a Firecracker escape on top of the kernel bug. The module isn't compiled in. We build custom minimal kernels for agent sandboxes. These run code interpreters, drive browsers and CLIs, power RL rollouts, and host long-running agents. CONFIG_CRYPTO_USER and CONFIG_CRYPTO_USER_API_AEAD have never been enabled, cause they're not needed by AI agents. ‍Fewer, purpose-built features mean fewer places for vulnerabilities.

@mathemagic1an @vercel Amazing shipping right here 🚢

Introducing THUNDERDOME ⚡️💀 Watch coding agents to fight to the DEATH in an E2B sandbox. Open source. BYOK. Built with @vercel, @e2b and gpt-5.5 in ~2 hours. Incredible time to be alive.

The Cognition team released an article describing the challenges of building an in-house AI agent. A big challenge is ensuring your agent can complete real work. Securely and at scale. That requires proper isolation and running agents in specialized machines. The good news: if you run your agents on @e2b, you get over three years of work on this problem out of the box. Hard won lessons and integrated into your agent in an afternoon.

@mlejva @EricNewcomer That's a great view indeed.

They say NYC has great views. I agree. Once again, big thanks to WingVC and @EricNewcomer for featuring @e2b as one of the 2026 Enterprise Tech 30 companies.

This was a fun side quest - our own @mlejva just rang the Nasdaq bell with the rest of the Enterprise Tech 30 winners. Grateful to be included on the list!

@MinzuBox welcome to the community! excited to have you with us

We just got accepted into the @e2b for Startups program. We received $20K in credits plus access to the E2B Pro tier. We’re putting this support into MinzuBox, our AI-powered platform for creating personal no-code apps and running general computer tasks in minutes.

Thank you @e2b for having us last month as part of their campaign on 🚌 stops all over SF

@lukeshiels @interfere_ x @e2b 🫡

@mlejva @OpenAI 🔥🔥🔥 release from the team as always.

OpenAI x e2b: Build your agents with the new OpenAI Agents SDK, powered by @E2B Sandboxes. Excited to support @OpenAI as a launch partner!

@OpenAIDevs Loved collaborating on this one: The Agents SDK x E2B guides & demos in the thread. x.com/e2b/status/204…

Build long-running agents with more control over agent execution. New capabilities in the Agents SDK: • Run agents in controlled sandboxes • Inspect and customize the open-source harness • Control when memories are created and where they’re stored

Sandboxing is currently supported in the Python Agents SDK (stay tuned for TypeScript!) Get started today: e2b.dev/blog/e2b-is-no…

Another example, in this case with computer use:

OpenAI x E2B: build your agents with the new OpenAI Agents SDK, powered by E2B sandboxes. We're excited to support OpenAI as a launch partner! The new @OpenAI Agents SDK will now get dedicated sandboxes - perfect for persistent, long-running agents. With E2B, you'll get a custom environment with resource isolation and security boundaries, with no infrastructure setup required. Your agents will be able to: - Edit files and run shell commands in isolated environments - Maintain temporary workspace state across steps - Produce artifacts you can review before publishing - Run multiple sandboxes in parallel for concurrent workloads - Generate frontend output with live preview URLs ... and more, with a few lines of code! Learn more and see the end-to-end example in the thread: