E2B (@e2b) header
E2B (@e2b) profile picture

Machines for AI agents | Hiring! 👉 https://nitter.cf/t.co/WTLBOEvNRx

Computers
Joined April 2023
Photo by E2B (@e2b)Photo by E2B (@e2b)Photo by E2B (@e2b)Photo by E2B (@e2b)Photo by E2B (@e2b)Photo by E2B (@e2b)Photo by E2B (@e2b)Photo by E2B (@e2b)Photo by E2B (@e2b)Photo by E2B (@e2b)
Pinned Tweet
We just passed $120M ARR. 🚀 It started in a Prague apartment, where @mlejva and @co_valenta paid rent with hackathon prize money. Thank you to everyone building on E2B. 🧡 Next stop: making agents even easier to build, run, and scale. businesswire.com/news/home/2…
16
6
8
73
105,770
Two new integrations landed in the E2B Cookbook this week: Hatchet and Anchor Browser. 1. Hatchet Use @hatchet_dev with E2B to run background jobs and agents reliably, with every step executing in its own isolated sandbox. Long-running agent jobs rarely fail cleanly. A model call times out, a worker restarts, a step crashes halfway through. Hatchet handles scheduling, retries, and recovery, so a single failure is retried instead of bringing down the entire run. Hatchet decides when each step runs and how to recover when it fails. E2B gives each step a secure, isolated machine for agent-generated code. Steps run in parallel without interfering with one another, and a crash inside a sandbox stays inside it. The result is agent pipelines that are both reliable and safe. Check out the cookbook example- a Hatchet durable task runs Python in an E2B sandbox, kills it, and reconnects to find its files intact: github.com/e2b-dev/e2b-cookb… 2. Anchor Browser Use Anchor Browser with E2B to give your agents a cloud browser that can navigate websites, sign in, and complete tasks across web apps, while the sandbox stays lightweight. Much of the most valuable work on the web sits behind a login, and many sites block bots outright. @AnchorBrowser gives agents safe, managed access, with built-in authentication, stealth, and proxies, so they can reach the apps they need. Paired with E2B, your agent has both halves of a computer. The sandbox is where it installs packages, runs scripts and calls models. Anchor is where it browses the web like a person, signed in to real apps. In a single run, an agent can pull data from a web app and process it in code. Because the browser runs as a managed Anchor session instead of the sandbox, sandboxes start faster and you can watch every session live. Get started with the cookbook example: github.com/e2b-dev/e2b-cookb…
1
1
15
1,196
Agents need an easy, secure way to work with files. Last week at BoxWorks, @Box announced a cleaner way to give them access: Box Mount. With Box Mount, a Box folder shows up as a local directory inside an E2B sandbox. Claude reads the contract there, checks it against your legal playbook, and the review memo syncs back to Box in seconds. Box keeps the files. The agent runs in E2B and never sees your Box credentials. Check out the example: github.com/e2b-dev/e2b-cookb…
5
5
1
35
1,818
At 14, Jakub built the second-largest Minecraft server in Czechia: own racks, own cluster, millions of players. Now he's Lead Platform Engineer at E2B, building the system behind billions of sandboxes 👇 youtube.com/shorts/PKfC9vnG5…
5
3
1
32
1,237
Start building with Gemini managed agents + E2B: docs.e2b.dev/agents/gemini-m…
building with Managed Agents on the Gemini API? now you can bring your own sandbox with self-hosted environments start building today: ai.studio
1
3
17
1,115
Give 1,000 agents 1,000 machines. Let them run for an hour, snapshot them, and try 1,000 different approaches. Matt on our product team is building toward that: environments you can pause, resume, and fork 👇 youtube.com/shorts/Y__YQ1KXH…
7
8
1
34
18,958
As an independent benchmarking company, @ArtificialAnlys depends on fair, repeatable tests. That means giving every model a clean environment, with no leftover files or state to skew its score. E2B provides that environment through an isolated sandbox for each benchmark task, supporting runs that last anywhere from seconds to more than nine hours. The same infrastructure powers Optima, Artificial Analysis’s recently launched product that lets enterprises build custom benchmarks using their own files, agent traces, or coding environments. With sensitive enterprise data involved, the team closely evaluated E2B and was confident it met the requirements of their enterprise customers. youtube.com/watch?v=M3h3kC1o…
3
6
23
32,875
"Security is very core to how we think about our infrastructure at Artificial Analysis. We’re dealing with access to pre-release models, and so we can’t have any concerns around the security of sandboxes." - George Cameron @grmcameron, Co-Founder and CPO, Artificial Analysis
1
5
343
We’re excited to pair @nvidia Vera’s faster compute with E2B’s simple SDK to give agents fast, isolated computers. With 1.5× single-thread compute throughput vs. our AMD EPYC 9B45 reference in our tests, we’re looking forward to building more together! 🚀 e2b.dev/resources/nvidia-ver…
1
6
3
41
4,053
Was a pleasure working with the @e2b team on this. Agents are a new type of customer that you must be able to sell to frictionlessly, and @mpp on Tempo is the fastest, cheapest and simplest way to go about it. I know how I'll be running my evals now!
Your agents can now pay for E2B sandboxes with stablecoins on @tempo wallet. The agent never holds the wallet’s key, and you can see every payment it makes. In the demo, an agent pays for its own E2B sandbox and uses it as a remote machine. Try it: docs.e2b.dev/use-cases/agent… and get 5% off as part of the launch. Shoutout to @privy_io for powering the wallet E2B uses to receive stablecoin payments.
4
3
45
4,971
Your agents can now pay for E2B sandboxes with stablecoins on @tempo wallet. The agent never holds the wallet’s key, and you can see every payment it makes. In the demo, an agent pays for its own E2B sandbox and uses it as a remote machine. Try it: docs.e2b.dev/use-cases/agent… and get 5% off as part of the launch. Shoutout to @privy_io for powering the wallet E2B uses to receive stablecoin payments.
19
8
11
69
17,917
No other company can do what E2B does to help Agents continuously optimize the tools they use. Congratulations to @E2B @mlejva
We hit an annualized run rate of $120M in October. This year alone, we’re projected to add around $150M in net new revenue. This is an amazing milestone and a testament to the work of the @e2b team. I’m particularly excited about two things: 1/ This showcases how strong the tailwinds of AGL (Agent-Led Growth) can be. If you build a tool for agents and optimize your whole growth engine to serve them, you can see tremendous growth. This isn’t something you can just throw money at and buy. Agents don’t decide based on ads. You need a sophisticated growth engine that fine-tunes things like your AEO. I think this is what all future B2B devtool sales will look like. Increasingly, decisions about tool adoption will be made by agents, not humans. 2/ The use cases we’re serving. The majority of our revenue and usage comes from agents running in production. Not RL. When we started, we had two theses: (i) code is all you need—all agents will use code to complete tasks (which has turned out to be true); and (ii) sandboxes for agentic workloads will be a bigger market than sandboxes for RL workloads, but takeoff will be slower (still playing out). In the past 30 years, every company has become a software company. In the next 10 years, every company will have become an agent company. We’re building an infrastructure layer to power all these agents.
1
4
1
29
195,325
We hit an annualized run rate of $120M in October. This year alone, we’re projected to add around $150M in net new revenue. This is an amazing milestone and a testament to the work of the @e2b team. I’m particularly excited about two things: 1/ This showcases how strong the tailwinds of AGL (Agent-Led Growth) can be. If you build a tool for agents and optimize your whole growth engine to serve them, you can see tremendous growth. This isn’t something you can just throw money at and buy. Agents don’t decide based on ads. You need a sophisticated growth engine that fine-tunes things like your AEO. I think this is what all future B2B devtool sales will look like. Increasingly, decisions about tool adoption will be made by agents, not humans. 2/ The use cases we’re serving. The majority of our revenue and usage comes from agents running in production. Not RL. When we started, we had two theses: (i) code is all you need—all agents will use code to complete tasks (which has turned out to be true); and (ii) sandboxes for agentic workloads will be a bigger market than sandboxes for RL workloads, but takeoff will be slower (still playing out). In the past 30 years, every company has become a software company. In the next 10 years, every company will have become an agent company. We’re building an infrastructure layer to power all these agents.
84
24
21
325
421,149
One line of code spins up a sandbox. Need a thousand? It just scales. Our CTO and cofounder, @co_valenta, on how E2B runs agents anywhere, at any scale 👇 youtube.com/shorts/nZlT1FAYW…
7
6
39
1,432
We're a launch partner in the new @FireworksAI_HQ Frontier Ecosystem. Fireworks fine-tunes and serves open models fast. E2B gives agents built on those models a full Linux machine to run code, use tools, analyze data, and browse the web. Build with both to give your agents fast open models and a full machine to put them to work. Docs: docs.e2b.dev/quickstart/conn…
The future of AI is specialized intelligence with models tuned to your data, your domain and your customers. Today, we're proud to launch live from Forge the Fireworks Frontier Ecosystem with 60+ partners across the AI stack, helping you build and ship faster. Check it out: fireworks.ai/partners
1
4
1
33
1,820
Introducing E2B Workload Identity. Every sandbox now gets a signed identity, so your backend knows exactly which sandbox is calling and what it can access. No long-lived credentials to distribute or rotate. Generally available on E2B Cloud, supported in BYOC 👇 e2b.dev/resources/introducin…
9
7
3
31
2,883
We're excited to announce our AI Engineer Code Summit speaker lineup! → ai.engineer/code VP Gemini Post-Training Lead, @GoogleDeepMind CEO, @e2b CTO, @ExaAILabs CEO, @warpdotdev CEO, @aviator_co_ CEO, @fivetran CTO, @Lovable CTO, @iamovercut CTO, @earendilworks (Pi) CEO, @diffusionio CPO, @cognition CTO, @GoodfireAI MTS, @AnthropicAI CTO, @composio GPM, @Cloudflare MTS, @databricks CEO, @AmpCode Co-Founder, @gimletlabs CEO, @mixedbreadai CEO, @humanlayer_dev Head of AI, @MonacoGTM Lecturer, @UCBerkeley Principal Engineer, @SpaceXSI CEO, @TypeSafeAI (Jev) Founder, Bun at Anthropic VP Product, @reflection_ai Research Lead, Reflection AI Staff Software Engineer, @SonarSource Principal Software Engineer, @tryramp Senior Engineering Manager, @netflix Forward Deployed Engineer, @baseten Also joining us: @kevinhou22 — Google DeepMind Antigravity @Steve_Yegge — Creator of Beads & Gas Town @lucasmeijer — AgentsInTheCloud.com @kentcdodds — Software Engineer & Educator @trq212 — Independent @simonw — Django, Pelicans, Lethal Trifecta Presented by Google DeepMind. November 10–12 in San Francisco. Attendance is by application. → ai.engineer/code
7
7
6
45
20,710