E2B provides open-source Firecracker-microVM sandboxes for AI agents. It is offered as a hosted API, as BYOC, and since September 2026 as a self-hostable single-node package (E2B Embed). In 2026 it became a supported sandbox provider in the OpenAI Agents SDK and published integrations for Devin Outposts and Cursor Self-Hosted Machines. Vendor case studies show it used for RL rollouts (Paper Instruments) and large-scale evals (Arena).
Arena is the Berkeley Sky Computing Lab model-evaluation platform behind WebDev Arena, which E2B profiled earlier under the LMArena name. It runs WebDev, Code Arena and Agent Arena evaluations on E2B: up to 600k sandboxes a day, up from 300-400k. E2B provisioned thousands of extra concurrent sandboxes within 24 hours ahead of Arena's June 2026 Agent Mode launch. Vendor-published.
Why it matters: A large public model-evaluation platform depends on E2B, which is a scale signal for eval and benchmark workloads (self-claimed).
Packages the E2B stack to run on a single machine inside a customer's environment, using Docker Compose, Terraform (GCP/AWS) or Kubernetes. No E2B account or license key is needed, and one setting exports metrics, traces and logs over OpenTelemetry. The changelog lists Embed from 2026-09-14, and the launch post is dated 2026-09-30.
Why it matters: Gives regulated buyers a deployment that stays inside their own environment, and lets labs self-host with no vendor dependency. It runs on one machine only; scaling across machines uses BYOC.
A reference architecture in which OpenAI provides the model, harness and session lifecycle and E2B provides per-chat Firecracker sandboxes, with pause and fork implemented through snapshots.
Why it matters: Strengthens E2B's position inside the OpenAI agent stack.
Workspaces bring projects and access management together in one place. New cursor-agents dispatcher and worker templates run Cursor Self-Hosted Machines on E2B. Guides were published for Agno, NVIDIA NeMo Gym and Muse Code.
Why it matters: The NeMo Gym guide connects E2B to an open RL environment framework. The Cursor templates come from E2B and are not a confirmed Cursor partnership.
Paper Instruments trains models for consulting, finance, investment banking and law work. It runs thousands of concurrent RL rollouts (GRPO/CISPO) on E2B and snapshots both filesystem and memory of running servers to start faster. Vendor-reported: up to 3x faster tool execution than other sandbox providers it evaluated.
Why it matters: The first named, vendor-published case study of E2B used directly as RL training infrastructure. The performance figure is self-claimed.
The network.egressProxy option sends all outbound TCP traffic through a customer SOCKS5 proxy. Sandbox.list gains order, startedAfter and template filters, and snapshot-management CLI commands were added.
Why it matters: Gives network-control options that enterprise security reviews look for.
Sandbox.create takes an `iam` option for short-lived workload identity tokens. Python SDK 2.38.0 adopts the Rust-based pyqwest transport. Sandbox placement errors now return machine-readable codes.
Why it matters: Improves credential hygiene for agents that call cloud APIs.
Access tokens were disabled as of 2026-08-01, and non-Debian base images were added for templates. API-key validation moved server-side on 2026-08-31.
Why it matters: A breaking authentication change for older integrations. Wider OS coverage helps people building environments.
In 'Use E2B as the Execution Layer For Devin Outposts', each Devin session runs on an E2B microVM inside the customer's cloud boundary. CPU, RAM and disk are configurable, and snapshots allow pause and resume. The post does not mention Cognition or a formal partnership.
Why it matters: Gives teams that run Devin a BYOC execution option. It is an integration guide published by E2B, not a confirmed Cognition partnership.
A running sandbox can now be forked into one or more clones from its exact in-memory state, and listSnapshots accepts a name filter. A CLI command, `e2b sandbox fork`, followed on 2026-09-21.
Why it matters: Forking a running environment helps RL rollouts and branching agent search.
Rogo, a financial-services AI company, pairs Anthropic's Claude Managed Agents with E2B sandboxes. The case study cites 10,000-15,000 concurrent sandboxes. Vendor-published, so self-claimed.
Why it matters: Shows E2B as the execution layer next to Anthropic's managed-agent product in a financial-services deployment. This is a customer's stack choice, not a direct E2B-Anthropic contract.
E2B joined the Stripe Projects developer preview as a partner, implementing the Agentic Provisioning Protocol. Agents can provision and authenticate sandboxes with `stripe projects add e2b`, with no signup flow or manual API-key step.
Why it matters: Agents can get compute without a human in the loop, which simplifies automated pipelines.
StackAI, a no-code enterprise agent-workflow platform, replaced its homegrown code-execution sandbox with E2B. Co-founder Tony Rosinol is quoted saying the old system had taken up 5-6 platform engineers. Vendor-published, so self-claimed.
Why it matters: A vendor-published signal of adoption by enterprise agent platforms that handle sensitive data.
E2B says each sandbox runs in its own Firecracker microVM with its own kernel, and that its minimal custom kernels do not compile in the vulnerable algif_aead module. This is the vendor's own security claim.
Why it matters: Security teams get a concrete comparison of microVM isolation against shared-kernel containers for running untrusted agent or RL code.