E2B vs Isorun
Choose E2B for code interpreters and short-to-medium-lived agent tasks that need microVM isolation, with an open-source self-host path; choose Isorun for agents that need full Linux VMs from any pinned OCI image, with fork, hibernate and API keys kept out of the guest. E2B uses Firecracker microVM isolation and is open source; Isorun uses KVM microVM isolation.
Key differences between E2B and Isorun
- Isolation: E2B uses Firecracker microVM; Isorun uses KVM microVM.
- Open source: E2B is open source (Apache-2.0); Isorun is not.
- Session length: 1 h / 24 h (Pro) (E2B) versus 300 s idle timeout (default) (Isorun).
- SDKs and interfaces: Only E2B lists Python. Only Isorun lists REST API and MCP server.
What they have in common
- Both are hosted platforms.
- Both use microVM isolation.
- Both support snapshots.
- Both can pause and resume a sandbox.
- Both list TypeScript.
E2B vs Isorun at a glance
| Attribute | E2B | Isorun |
|---|---|---|
| What it is | Open-source cloud sandboxes for AI agents, each a Firecracker microVM, with pause/resume, snapshots and forking. | Hosted KVM microVM sandboxes booted from pinned OCI images, with fork of a running VM, hibernate/resume, host-side egress rules and credential injection. |
| Type | Hosted platform | Hosted platform |
| Isolation | Firecracker microVM with its own kernel per sandbox | KVM microVM per sandbox with its own guest kernel; the docs do not name the hypervisor. Egress policy and the credential proxy are enforced on the host, outside the guest |
| Open source | Yes (Apache-2.0) | No |
| Self-host / BYOC | Yes / Yes | Not documented / Not documented |
| SDKs | Python, JavaScript/TypeScript | JavaScript/TypeScript, REST API, MCP server |
| Cold start (vendor claim) | Not documented | Homepage: VMs "ready in 10ms" (vendor claim); the API reference example shows create_ms of 9. The first time a runner sees an image it pulls and prepares it, which the docs say takes 10 to 60 seconds |
| Max session | Up to 1 hour continuous (Hobby), 24 hours (Pro) or custom (Enterprise); pausing resets the clock and paused sandboxes are kept until deleted | No maximum lifetime documented. Each sandbox has an idle auto-destroy timer, 300 seconds by default, set per create with timeoutSec or extended with setTimeout(); passing 0 disables it |
| Persistence | Pause/resume preserves filesystem and memory; snapshots of running sandboxes, forking from a snapshot, filesystem-only snapshots, auto-resume and volumes (beta) | The image is mounted read-only with a writable scratch layer (4 GiB by default) that lasts for the sandbox's lifetime, including across hibernate/resume. Hibernate keeps filesystem, memory and running processes. Snapshots persist until deleted and restore on any runner in the same region. Optional named persistent disks (ext4 on Tigris Cloud Disk with a local NVMe cache) mount at /workspace, outlive sandboxes and can be snapshotted and forked copy-on-write |
| Snapshots / pause | Yes / Yes | Yes / Yes |
| GPU | No — sandboxes are CPU-only | Not documented |
| Networking | Internet on by default; can be disabled or restricted with allow/deny lists of IPs, CIDRs and domains; public sandbox URLs for exposed ports; custom domains and published egress IPs | Egress is unrestricted by default; per-sandbox allow/deny rules (CIDRs, IPs, hostnames matched on SNI, wildcards) or named profiles (unrestricted, locked-down, claude-code, openai) are enforced at the host boundary. A host-side proxy injects API keys for OpenAI, Anthropic, Google, GitHub and Hugging Face so the guest only sees placeholders, with optional method and path rules. sandbox.url(port) proxies any port over HTTPS and WebSocket; the docs differ on whether these URLs require the API key |
| Pricing | Per second: $0.000014 per vCPU-second (~$0.050/vCPU-hour) + $0.0000045 per GiB-second (~$0.016/GiB-hour). Pro plan $150/month plus usage; Enterprise from $3,000/month | Per-second billing with no minimums: $0.025 per vCPU-hour plus $0.015 per GiB-hour of RAM ($0.040 an hour for the default 1 vCPU + 1 GiB; 8 vCPU + 16 GiB is $0.440 an hour). Hibernated sandboxes are not billed for runtime. Persistent disks: $0.02 per GB-month of data stored. The homepage says egress traffic and platform fees are included |
| Free tier | Hobby plan: $100 one-time credit, 10 concurrent sandboxes, 1-hour sessions | $50 of credit on sign-up, no card required (about 1,250 hours of a 1 vCPU + 1 GiB sandbox) |
| Compliance | SOC 2 Type II; HIPAA BAA and DPA available on request | SOC 2 Type II listed as "(soon)" on the homepage; each sandbox has an HMAC-chained, tamper-evident audit log |
| Regions | Default region plus a shared EU cluster on request | Organizations are scoped to a US or EU region at sign-up; the API key routes to that region's runner |
| Company headquarters | San Francisco, California, United States | Not documented |
| Good fit for | Code interpreters and short-to-medium-lived agent tasks that need microVM isolation, with an open-source self-host path | Agents that need full Linux VMs from any pinned OCI image, with fork, hibernate and API keys kept out of the guest |
Verified November 14, 2026 (E2B) and November 18, 2026 (Isorun) from each provider’s documentation. Cold-start figures are vendor claims, not our measurements.
Which should you choose?
Reasons to choose E2B
- You want the most widely integrated agent sandbox, with a large ecosystem of examples
- You need Firecracker microVM isolation for untrusted multi-tenant code
- You want an open-source codebase you can self-host or run via BYOC
- You want ready-made code-interpreter and desktop SDKs
Reasons to choose Isorun
- You want each sandbox to be a microVM with its own kernel, booted from any pinned OCI image.
- You need to fork a running sandbox with its memory intact to branch an agent's work.
- You want third-party API keys kept outside the VM and egress restricted at the host.
- You want per-second billing with no charge while a workspace is hibernated.
Trade-offs to check first
- E2B: CPU-only — no GPUs
- E2B: Session length capped at 1 hour on the free plan and 24 hours on Pro
- Isorun: Only a TypeScript SDK today; the Python SDK is described as in development.
- Isorun: The hypervisor, GPU support and a maximum session length are not documented.
Both are worth piloting with your own image and region. See the full E2B profile and Isorun profile, or the complete comparison.
More comparisons
Frequently asked questions
Is E2B or Isorun better for AI agents?
What is the difference between E2B and Isorun?
Which is open source, E2B or Isorun?
How do E2B and Isorun isolate code?
How does E2B pricing compare with Isorun?
Do E2B and Isorun support GPUs?
Can you self-host E2B or Isorun?
How long can sessions run on E2B and Isorun?
Do E2B and Isorun support snapshots or pause and resume?
Sources
Check before you rely on it. Products change quickly, and this page reflects public documentation as of November 18, 2026. Confirm anything that matters in the provider’s own documentation.
Cite this page
Agent Sandboxes. (2026). E2B vs Isorun. agentsandboxes.org. Last reviewed November 18, 2026. https://agentsandboxes.org/compare/e2b-vs-isorun/