# Vercel Sandbox alternatives

Teams look past Vercel Sandbox when the loop they wrote around it, clone, run Claude Code, push a branch, open a pull request, has become the product they maintain.

Facts checked 17 October 2026. Prices and limits move. Read the citations.

Rush is our product and is listed first. Every other row is from the vendor's own pages, retrieved on the date beside it.

## The useful distinction

Teams look past Vercel Sandbox when the loop they wrote around it, clone, run Claude Code, push a branch, open a pull request, has become the product they maintain.

A sandbox is a computer for an agent. You still write the agent loop, clone the repository, push the branch and decide when the work is done. Rush is the layer above: you send the task and get back the pull request, report or files.

## What Rush is

Rush is the managed version of the loop most teams write on Vercel Sandbox: start Claude Code or Codex on a repository and get the pull request back.

## If you… use… not if

| If you | Use | Not if |
| --- | --- | --- |
| You want to send a task by API or MCP and get back a pull request, report or files with the transcript. | Rush | You need to self-host, use GitLab or Bitbucket, or bring an agent loop of your own. |
| You are building your own agent product and want raw microVM sandboxes with an SDK. | E2B | You want the task done and a pull request back without writing the loop. |
| You need many sandbox shapes (Linux, Windows, macOS, GPU) under one SDK, or your own runners. | Daytona | You want an agent to finish the task and hand back a pull request. |
| You need GPUs in the sandbox or very large fan-out for RL rollouts and evals. | Modal Sandboxes | The job is one agent on one repository, ending in a pull request. |
| You are building an agent platform and need credentials kept out of the sandbox, a VPC deploy or RL fine-tuning. | Runloop | You want to send a task and get a pull request without writing orchestration. |
| You are already on Workers, R2 and Durable Objects and want sandboxes next to them. | Cloudflare Sandbox | You want a pull request back, not a diff to commit yourself. |
| You build agents inside AWS and need Cedar policy, corporate identity, CloudTrail and evaluations. | Amazon Bedrock AgentCore | You want Claude Code or Codex to do a task on a repository and return a pull request. |

## The field

| Tool | Job | What runs | Isolation | Proof | Price | Taps out |
| --- | --- | --- | --- | --- | --- | --- |
| Rush | Send a task by API; an agent does it in its own sandbox | Claude Code, Codex or OpenCode | One E2B microVM per run | PR with checks, artifacts, transcript; else needs_review | Free 5 agent-hours / month, then $20 Pro | Three harnesses. GitHub repos only. No self-host. |
| Vercel Sandbox | Firecracker sandboxes from Vercel's SDK and CLI | Your agent (coding agents in the image) | Firecracker microVM | None; you open the PR | Hobby free 5 CPU-h; Pro from $20 credit | 24 h sessions on Pro, 45 min on Hobby. |
| E2B | SDK for microVM sandboxes your agent runs in | Your agent (Claude Code template ships) | Firecracker microVM | None; you read git diff | Hobby $0 + $100 credit; Pro $150 / mo + usage | 1 h Hobby, 24 h Pro sessions. No PR layer. |
| Daytona | Elastic sandboxes for AI-generated code | Your agent | Container by default; VM opt-in | None; you push and open the PR | $200 free, then per second | 15-min auto-stop. 4 vCPU / 8 GB ceiling. |
| Modal Sandboxes | Serverless sandboxes for agents, RL and untrusted code | Your agent | gVisor, or VM runtime | None; you build it | Starter $0 + $30 credit; Team $250 / mo | 5-min default, 24 h cap per sandbox. |
| Runloop | Devboxes and SDK for software engineering agents | Your agent; Claude Code and ACP adapters | VM per Devbox | None; you open the PR | Basic free + $50 credit; Pro $250 / mo | You write the loop. VPC on Enterprise. |
| Cloudflare Sandbox | MicroVM containers started from a Worker | Your agent | Firecracker microVM | None; tutorial returns a diff | Workers Paid $5 / mo + per second | 4 vCPU / 12 GiB max. Worker per sandbox. |
| Amazon Bedrock AgentCore | AWS platform to host and govern agents | Any framework; Strands-based harness | MicroVM per session | None; API response | $0.0895 / vCPU-h; $200 credit for new AWS | 8 h sessions. You assemble the parts. |

## In depth

### E2B

Hobby $0 with a one-time $100 credit; Pro $150 / month plus usage. Checked 17 October 2026.. You are building your own agent product and want raw microVM sandboxes with an SDK.

Firecracker microVM sandboxes driven from an SDK. Your agent runs code there; the loop, the git steps and the pull request are your code. Rush itself runs on E2B.

Left to you. E2B's Claude Code guide clones with your token, runs the agent and reads git diff; pushing and opening the pull request is your code.

**Taps out.** Sessions end at 1 hour on Hobby and 24 hours on Pro unless paused. Sandboxes reach the open internet by default. No result or pull request layer. Pro has a $150 monthly fee before usage.

### Daytona

$200 of free compute, then pay as you go with no monthly fee. Checked 17 October 2026.. You need many sandbox shapes (Linux, Windows, macOS, GPU) under one SDK, or your own runners.

Elastic sandboxes for AI-generated code: Linux containers by default, with VM, Windows, macOS and GPU options, SDKs in five languages, an MCP server and BYOC.

Left to you. The git API clones, branches, commits and pushes; opening the pull request is your code.

**Taps out.** Default runtime is a container, and container sandboxes cannot pause memory. The 15-minute auto-stop does not count a running process as activity. The open-source repository stopped receiving updates in June 2026.

### Modal Sandboxes

Starter $0 + compute with $30 / month credit; Team $250 / month + compute. Checked 17 October 2026.. You need GPUs in the sandbox or very large fan-out for RL rollouts and evals.

Programmable gVisor containers, or a VM runtime, on Modal's serverless cloud, for agent code, RL rollouts and untrusted code, with snapshots, egress rules and GPUs.

Left to you. The sandbox guide has no git or pull request feature.

**Taps out.** 5-minute default lifetime and a 24-hour cap per sandbox. Sandbox CPU costs about three times a Modal function's. GPU sandboxes need the gVisor runtime.

### Runloop

Basic free with $50 of credits; Pro $250 / month plus usage. Checked 17 October 2026.. You are building an agent platform and need credentials kept out of the sandbox, a VPC deploy or RL fine-tuning.

VM-isolated Devboxes for software engineering agents, with blueprints, snapshots, an MCP Hub, Agent Gateways that hide API keys, and a Remote Agents SDK.

Left to you. Code Mounts pull a repository or branch in; opening the pull request is your code.

**Taps out.** You still write the agent loop. Suspend and resume and repo connections are listed under the $250 Pro plan. VPC deploy is Enterprise only.

### Cloudflare Sandbox

Workers Paid $5 / month, with 375 vCPU-minutes and 25 GiB-hours included. Checked 17 October 2026.. You are already on Workers, R2 and Durable Objects and want sandboxes next to them.

Linux microVM containers, or isolated Dynamic Workers, started from a Worker to run untrusted or agent-generated code. You build the agent loop.

Left to you. Cloudflare's coding agent runner tutorial clones a repository, runs Claude Code and returns a diff, with the instruction not to commit.

**Taps out.** Needs Workers Paid and a Worker and Durable Object around each sandbox. Largest instance is 4 vCPU and 12 GiB. The tutorial ends at a diff, with no pull request or proof.

### Amazon Bedrock AgentCore

Runtime $0.0895 per vCPU-hour and $0.00945 per GB-hour; up to $200 Free Tier credit for new AWS customers. Checked 17 October 2026.. You build agents inside AWS and need Cedar policy, corporate identity, CloudTrail and evaluations.

A modular AWS platform to host, run and govern agents of any framework: a microVM runtime, a managed harness, gateway and MCP, memory, identity, browser, code interpreter, policy and evals.

Left to you. Results come back over the API, a stream or a WebSocket; GitHub appears only as an outbound sign-in target.

**Taps out.** 8-hour microVM sessions. The managed harness is Strands-based, not the Claude Code or Codex CLI. No pull request or proof loop: you assemble Runtime, Gateway, Identity and Observability.

## Skip Rush if

- Rush runs three agents: Claude Code, Codex and OpenCode. It does not host an agent you wrote yourself.
- Repositories come through the Rush GitHub App. A GitLab or Bitbucket repository cannot be a run's repository yet.
- There is no self-hosted or customer-VPC deployment, and we do not publish a compliance report today.
- Compute is metered. Free includes 5 agent-hours a month and Pro 40, each with a weekly ceiling.
- You review the pull request. Rush does not merge for you.

## Questions people actually ask

### What is the best Vercel Sandbox alternative?

It depends on the part of the job you want to keep. Use E2B if you are building your own agent product and want raw microVM sandboxes with an SDK. Use Daytona if you need many sandbox shapes (Linux, Windows, macOS, GPU) under one SDK, or your own runners. Use Modal Sandboxes if you need GPUs in the sandbox or very large fan-out for RL rollouts and evals. Use Rush if you want to send a task by API or MCP and get back a pull request, report or files with the transcript.

### Can I move from Vercel Sandbox to Rush?

Yes. The steps, from Vercel's own docs, are on the Migrate from Vercel Sandbox to Rush page. Code you already pushed stays where it is.

### Where does the code go when I leave?

Anything pushed to your GitHub remote stays there. That is the off-ramp on every product in this set, including Rush.

## Keep reading

- [Rush vs Vercel Sandbox](https://getrush.ai/compare/rush-vs-vercel-sandbox.md)
- [Migrate from Vercel Sandbox to Rush](https://getrush.ai/compare/migrate-from-vercel-sandbox.md)
- [Rush vs E2B](https://getrush.ai/compare/rush-vs-e2b.md)
- [Rush vs Daytona](https://getrush.ai/compare/rush-vs-daytona.md)
- [Rush vs Modal Sandboxes](https://getrush.ai/compare/rush-vs-modal.md)
- [Rush vs Runloop](https://getrush.ai/compare/rush-vs-runloop.md)
- [Rush vs Cloudflare Sandbox](https://getrush.ai/compare/rush-vs-cloudflare-sandbox.md)
- [Rush vs Amazon Bedrock AgentCore](https://getrush.ai/compare/rush-vs-agentcore.md)

## Sources

1. Rush, "Rush product requirements", retrieved 2026-09-15. https://getrush.ai/cloud
2. Rush, "Rush pricing (live contract on getrush.ai)", retrieved 2026-09-15. https://getrush.ai/pricing
3. Rush, "Isolation, plainly", retrieved 2026-10-17. https://getrush.ai/docs/concepts/isolation
4. Rush, "Results and proof", retrieved 2026-10-17. https://getrush.ai/docs/concepts/results-and-proof
5. Rush, "Usage and billing", retrieved 2026-10-17. https://getrush.ai/docs/concepts/usage-and-billing
6. Rush, "Rush MCP server", retrieved 2026-10-17. https://getrush.ai/docs/concepts/mcp-server
7. Rush, "Automations", retrieved 2026-10-17. https://getrush.ai/docs/concepts/automations
8. Vercel, "Vercel Sandbox", retrieved 2026-10-17. https://vercel.com/docs/sandbox
9. Vercel, "Vercel Sandbox pricing and quotas", retrieved 2026-10-17. https://vercel.com/docs/sandbox/pricing
10. Vercel, "Run untrusted code with Vercel Sandbox, now generally available", published 2026-01-30. https://vercel.com/blog/vercel-sandbox-is-now-generally-available
11. Vercel, "Vercel Sandbox vs E2B", published 2026-03-20. https://vercel.com/kb/guide/vercel-sandbox-vs-e2b
12. Vercel, "Sandboxes (Vercel MCP tools)", retrieved 2026-10-17. https://vercel.com/docs/agent-resources/vercel-mcp/tools/sandboxes
13. E2B, "E2B Pricing", retrieved 2026-10-17. https://e2b.dev/pricing
14. E2B, "E2B | The Enterprise AI Agent Cloud", retrieved 2026-10-17. https://e2b.dev/
15. E2B, "Sandbox persistence", retrieved 2026-10-17. https://docs.e2b.dev/sandbox/persistence
16. E2B, "Claude Code - E2B Docs", retrieved 2026-10-17. https://docs.e2b.dev/agents/claude-code
17. E2B, "Coding Agents - E2B Docs", retrieved 2026-10-17. https://docs.e2b.dev/use-cases/coding-agents
18. E2B, "Available servers - E2B Docs", retrieved 2026-10-17. https://docs.e2b.dev/mcp-gateway/available-servers
19. E2B, "e2b-dev/infra (GitHub README)", retrieved 2026-10-17. https://github.com/e2b-dev/infra
20. Daytona, "Daytona - Secure Infrastructure for Running AI-Generated Code (pricing)", retrieved 2026-10-17. https://www.daytona.io/pricing
21. Daytona, "Sandboxes | Daytona", retrieved 2026-10-17. https://www.daytona.io/docs/en/sandboxes
22. Daytona, "Daytona MCP Server | Daytona", retrieved 2026-10-17. https://www.daytona.io/docs/en/mcp
23. Daytona, "Git Operations | Daytona", retrieved 2026-10-17. https://www.daytona.io/docs/en/git-operations
24. Daytona, "Bring Your Own Compute (BYOC) | Daytona", retrieved 2026-10-17. https://www.daytona.io/docs/en/bring-your-own-compute
25. Daytona, "daytonaio/daytona (GitHub README)", retrieved 2026-10-17. https://github.com/daytonaio/daytona
26. Modal, "Pricing: Pay per second for GPUs and CPUs | Modal", retrieved 2026-10-17. https://modal.com/pricing
27. Modal, "Sandboxes (Modal Docs)", retrieved 2026-10-17. https://modal.com/docs/guide/sandboxes
28. Modal, "Sandboxes: Isolated environments for reinforcement learning and AI agents | Modal", retrieved 2026-10-17. https://modal.com/products/sandboxes
29. Modal, "Networking and security | Modal Docs", retrieved 2026-10-17. https://modal.com/docs/guide/sandbox-networking
30. Modal, "Top AI Code Sandbox Products in 2025", published 2025-07-17. https://modal.com/blog/top-code-agent-sandbox-products
31. Runloop, "Runloop - Pricing", retrieved 2026-10-17. https://www.runloop.ai/pricing
32. Runloop, "Runloop - Your AI Agent Accelerator", retrieved 2026-10-17. https://www.runloop.ai/
33. Runloop, "Devbox Overview - Runloop AI Docs", retrieved 2026-10-17. https://docs.runloop.ai/docs/devboxes/overview
34. Runloop, "Runloop Features - Runloop AI Docs", retrieved 2026-10-17. https://docs.runloop.ai/docs/overview/runloop-features
35. Runloop, "MCP Hub - Runloop AI Docs", retrieved 2026-10-17. https://docs.runloop.ai/docs/devboxes/mcp-hub
36. Runloop, "Remote Agents SDK - Runloop AI Docs", retrieved 2026-10-17. https://docs.runloop.ai/docs/axons/sdk
37. Cloudflare, "Sandboxes on Cloudflare", retrieved 2026-10-17. https://developers.cloudflare.com/sandbox/
38. Cloudflare, "Choose a sandbox environment", retrieved 2026-10-17. https://developers.cloudflare.com/sandbox/concepts/
39. Cloudflare, "Pricing (Containers)", retrieved 2026-10-17. https://developers.cloudflare.com/containers/platform/pricing/
40. Cloudflare, "Limits (Containers)", retrieved 2026-10-17. https://developers.cloudflare.com/containers/platform/limits/
41. Cloudflare, "Build a coding agent runner", retrieved 2026-10-17. https://developers.cloudflare.com/sandbox/tutorials/claude-code/
42. Cloudflare, "Cloudflare's own MCP servers", retrieved 2026-10-17. https://developers.cloudflare.com/agents/model-context-protocol/cloudflare/servers-for-cloudflare/
43. AWS, "Amazon Bedrock AgentCore - AWS", retrieved 2026-10-17. https://aws.amazon.com/bedrock/agentcore/
44. AWS, "Amazon Bedrock AgentCore Pricing - AWS", retrieved 2026-10-17. https://aws.amazon.com/bedrock/agentcore/pricing/
45. AWS, "Amazon Bedrock AgentCore is now generally available", published 2025-10-13. https://aws.amazon.com/about-aws/whats-new/2025/10/amazon-bedrock-agentcore-available/
46. AWS, "Overview (What is Amazon Bedrock AgentCore?)", retrieved 2026-10-17. https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html
47. AWS, "Host agent or tools with Amazon Bedrock AgentCore Runtime", retrieved 2026-10-17. https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agents-tools-runtime.html
48. AWS, "AgentCore harness", retrieved 2026-10-17. https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness.html
49. AWS, "Interact with web applications using Amazon Bedrock AgentCore Browser", retrieved 2026-10-17. https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/browser-tool.html