Compare · Agent sandboxes · verified 17 Oct 2026

Rush vs Runloop

Runloop is the closest of the sandbox vendors to Rush: it ships Claude Code adapters and an MCP Hub. You still write the agent loop.

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

Start a TaskAll comparison pages
Vendor agentDevin · Cursor · Copilot · Julessame jobRushYour harness, isolated, one PR
Isolated sandbox rooms, one per run
The short answer

Pick Runloop when you are building your own agent platform and need credential isolation or a VPC. Pick Rush when you want the task done and the pull request back.

Proof

A real Rush run

Console capture of a coding Task that opened a pull request. Not a mockup.

cloud.getrush.ai · run-af7b2434
Rush console reviewing a pull request

Read this first

The useful distinction

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

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.

Head to head

Buyer questions

QuestionRushRunloop
What runsClaude Code, Codex or OpenCode, the vendors' own CLIs, or a saved agent built on one.None by default. The Remote Agents SDK connects Claude Code over a broker and OpenCode or Goose over ACP; you drive them.
IsolationOne E2B microVM per run with its own disk, memory, desktop and browser. It parks between turns and is removed on cancel or after 7 idle days.Virtual machine isolation per Devbox. Devboxes suspend and resume; snapshots save the disk.
Result and pull requestA run on a repository works on its own branch and opens the pull request; a run whose checks fail ends needs_review, not completed. Reports and files come back as artifacts.Left to you. Code Mounts pull a repository or branch in; opening the pull request is your code.
MCPRush is an MCP server at api.prix.dev/mcp with 18 tools. A run also takes MCP servers by connection or inline.MCP Hub calls tools on any MCP server through one endpoint, with tool-level access control, and keeps server credentials out of the Devbox.
TeamEveryone in the org sees the same Projects and runs, with who started each. Automations start runs from GitHub events, schedules, webhooks and Linear.Pro adds repo connections and a Slack support channel. No shared task view on the pages we read.
Starting priceFree 5 agent-hours / month; Pro $20; Team $200Basic free with $50 of credits; Pro $250 / month plus usage
Where it taps outThree harnesses. Repositories through the GitHub App only. No self-host or customer VPC. A key runs 4 at once by default, up to 100.You still write the agent loop. Suspend and resume and repo connections are listed under the $250 Pro plan. VPC deploy is Enterprise only.

Decision

When each side wins

Rush wins when

  • You want to send a task and read the pull request, with no orchestration code of your own.
  • Parking a run and waking it with its memory is on every Rush plan, including Free with 5 agent-hours.
  • Every run keeps its transcript, artifacts and usage on one record.

Runloop wins when

  • You need model API keys and MCP tokens kept out of the sandbox: Agent Gateways proxy model calls and MCP Hub holds tool credentials.
  • You need the infrastructure in your own cloud account (Enterprise VPC deploy) and a SOC 2 claim.
  • You fine-tune or evaluate models against your own workload.

Rush

Where Rush sits

Runloop gives you the parts to run Claude Code yourself. Rush runs it: POST /o/{org}/sessions with the agent and the task, and the session record returns the pull request, the artifacts and the transcript.

Honest limits

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.

FAQ

Questions people actually ask

Does Rush keep the API key out of the sandbox like Runloop's Agent Gateways?

Partly. A Rush header secret never enters the sandbox: the header is added to the run's HTTPS requests outside it. An env secret does reach the agent. Runloop proxies model calls for every key by design.

Can I move from Runloop to Rush?

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

Does Rush need my own model account?

By default a run uses your own Claude or ChatGPT subscription or API key, and your provider bills the model calls. Rush meters the sandbox compute against your plan, and parked time is free.

Cluster

Keep reading

Citations

Sources

Every factual claim on this page traces to one of these URLs. Retrieval date is 17 October 2026 unless the source prints an earlier published date.

  1. [1] Rush, “Rush product requirements”, retrieved 2026-09-15. https://getrush.ai/cloud
  2. [2] Rush, “Rush pricing (live contract on getrush.ai)”, retrieved 2026-09-15. https://getrush.ai/pricing
  3. [3] Rush, “Isolation, plainly”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/isolation
  4. [4] Rush, “Results and proof”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/results-and-proof
  5. [5] Rush, “Usage and billing”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/usage-and-billing
  6. [6] Rush, “Rush MCP server”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/mcp-server
  7. [7] Rush, “Automations”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/automations
  8. [8] Runloop, “Runloop - Pricing”, retrieved 2026-10-17. https://www.runloop.ai/pricing
  9. [9] Runloop, “Runloop - Your AI Agent Accelerator”, retrieved 2026-10-17. https://www.runloop.ai/
  10. [10] Runloop, “Devbox Overview - Runloop AI Docs”, retrieved 2026-10-17. https://docs.runloop.ai/docs/devboxes/overview
  11. [11] Runloop, “Runloop Features - Runloop AI Docs”, retrieved 2026-10-17. https://docs.runloop.ai/docs/overview/runloop-features
  12. [12] Runloop, “MCP Hub - Runloop AI Docs”, retrieved 2026-10-17. https://docs.runloop.ai/docs/devboxes/mcp-hub
  13. [13] Runloop, “Remote Agents SDK - Runloop AI Docs”, retrieved 2026-10-17. https://docs.runloop.ai/docs/axons/sdk

Next

Run the next Task on Rush

Connect a repository. Pick Claude Code, Codex, or OpenCode. Review the PR.

How the runtime works