# Best cloud coding agents

Most 2026 lists compare editors, terminals, and a single vendor agent. The useful split is the job: isolated cloud, live or unattended steer, a pull request, and what you can show a reviewer when the run stops.

Facts checked 15 September 2026. Prices and limits move. Read the citations.

Rush is our product. It is one row: the multi-harness runtime. It is not 'the best agent.'

**The short answer.** Pick the engine first (Claude Code, Codex, Copilot, Devin, Cursor, Gemini, Amp, Factory). Then pick the runtime.

## The useful distinction

Most 2026 lists mix editors, terminals, and a single vendor agent. The useful split is the job: isolated cloud, a pull request, and what you can show a reviewer when the run stops.

Vendor merge rates are not a shared benchmark. Cognition's 67% (14 Nov 2025) and Cursor's 60% internal (2 Sep 2026) measure each vendor using itself.

## What Rush is

Rush is one row: the multi-harness runtime. It is not the best agent. It is the place the harness you already pay for runs as a team session.

## If you… use… not if

| If you | Use | Not if |
| --- | --- | --- |
| Already run Claude Code, Codex, or OpenCode | Rush, or the vendor web for a single harness | You wanted a new agent personality |
| Want an autonomous vendor engineer on tickets | Devin or Factory Droids | You must bring your own model keys (Devin) or you need published rate limits (Factory) |
| Want the editor you already pay for, off the laptop | Cursor Cloud Agents | You are on Hobby |
| The work is a GitHub issue in a well-tested repo | Copilot cloud agent or Jules | You need more than 59 minutes (Copilot) or a non-GitHub remote (both) |

## 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: a one-time $1 free credit, then Pro $40 per member | Three harnesses. GitHub repos only. No self-host. |
| Devin | Cognition's autonomous engineer on a ticket | Devin Brain + Devbox | Isolated VM per session | PR on your SCM | Pro $20 / mo; Teams $80 min | No BYO model keys. Opaque quotas. |
| Cursor Cloud Agents | Cursor Agent, unattended, in a cloud VM | Cursor Agent | Firecracker microVM | Draft PR + artifacts | Paid Cursor plan, from $20 / mo | Needs Cursor. Commands auto-run. |
| GitHub Copilot cloud agent | Issue-to-PR inside GitHub Actions | Copilot cloud agent | Ephemeral Actions VM | Draft PR + session logs | Paid Copilot, from $10 / mo | 59-minute cap. GitHub repos only. |
| Claude Code on the web | Claude Code, hosted by Anthropic | Claude Code | Anthropic VM (~4 vCPU / 16 GB) | GitHub branch + PR | Claude Pro $20 / mo and up | Research preview. Claude and GitHub only. |
| Codex cloud | OpenAI Codex in a ChatGPT cloud box | Codex | Container; agent phase offline by default | Diff + PR on GitHub/GitLab | ChatGPT Plus $20 / mo and up | API-key path has no cloud. |
| Factory Droids | Factory agent on a persistent computer | Droid | Managed 4 CPU / 8 GB computer | PR from Slack or the app | Pro $20; managed computers from Plus $100 | Unpublished rate limits. Own harness. |
| Google Jules | Async Gemini agent on a GitHub issue | Jules / Gemini | Fresh Ubuntu VM per task | GitHub PR | 15 tasks / day free; paid via Google AI | GitHub only. Individual Gmail plans. |
| Amp orbs | Amp agent on a remote machine | Amp | Fresh orb per thread | You push; gh pr create via AGENTS.md | Hobby free; Individual $20 + orb hours | Own harness. GHES unsupported. |

## In depth

### Rush

Free: a one-time $1 free credit, then Pro $40 per member. 15 September 2026.. Multi-harness teams who want a Project and a trajectory.

The hole in the 2026 SERP is a runtime that is not also an editor and not also a model. That is the Rush row.

**Taps out.** Three harnesses. GitHub repositories only.

### The vendor clouds

15 September 2026. Staying inside one company.

Devin, Cursor Cloud Agents, Copilot cloud agent, Claude Code on the web, Codex cloud, Factory, Jules, and Amp each sell a complete loop. Read the vs pages before you switch the engine and the runtime on the same day.

**Taps out.** Each page in this cluster names the tap-out.

## What we can chart

### Self-serve starting price (individual, USD / month)

List prices from vendor pages retrieved 15 September 2026. Rush's free plan is $1 free credit and Pro is $40 per member, so the bar is the entry price, not the bill.

- Rush: Free plan; $1 free credit
- Copilot Pro: $10
- Devin Pro: $20
- Cursor Pro: $20
- Claude Pro: $20
- ChatGPT Plus: $20
- Factory Pro: $20
- Amp Individual: $20

### Jules daily task caps (rolling 24 hours)

From jules.google/docs/usage-limits, retrieved 15 September 2026.

- Jules free: 15 / day, 3 concurrent
- Jules in Pro: 100 / day, 15 concurrent
- Jules in Ultra: 300 / day, 60 concurrent

### Amp orb standard hourly prices

From ampcode.com/docs/orbs/sizes-and-costs, retrieved 15 September 2026. Billed by the minute. Paused orbs cost nothing.

- a1.tiny: 1 CPU / 2 GB · $0.08
- a1.small: 2 CPU / 4 GB · $0.17
- a1.medium: 4 CPU / 8 GB · $0.33
- a1.large: 8 CPU / 16 GB · $0.66
- a1.xxlarge: 16 CPU / 32 GB · $1.32

## 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 is a one-time $1 free credit; Pro includes 40 cloud computer hours a month per member, with a weekly ceiling.
- You review the pull request. Rush does not merge for you.

## Questions people actually ask

### Can I use Rush and the vendor cloud side by side?

Yes. Many teams keep Claude Code on the web or Cursor Cloud Agents for a single-vendor loop and put Rush on the tasks that need a shared Project, a second harness, or a trajectory they can hand to a reviewer.

### Does Rush replace Claude Code or Codex?

No. Rush runs those binaries. You keep the seat or the key. Rush is the runtime.

### 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.

### Why is there no ranking?

A crown needs a shared benchmark. Vendor merge rates (Devin 67% in Nov 2025, Cursor 60% internal in Sep 2026) are not that benchmark. Scenario routing is.

## Keep reading

- [Devin alternatives](https://getrush.ai/compare/devin-alternatives.md)
- [Cursor Cloud Agents alternatives](https://getrush.ai/compare/cursor-cloud-agents-alternatives.md)
- [Best way to run Claude Code in the cloud](https://getrush.ai/compare/best-claude-code-cloud.md)
- [Cloud coding agents for engineering teams](https://getrush.ai/compare/engineering-teams.md)

## Run the next task on Rush

### Rush

- [How Rush runs each agent in its own cloud computer](https://getrush.ai/cloud/)
- [Rush plans and pricing](https://getrush.ai/pricing.md)
- [Quickstart: start a run with an API key](https://getrush.ai/docs/quickstart.md)
- [Turn a Linear label into a PR](https://getrush.ai/docs/use-cases/linear-label-to-pr.md)

### Connect your tools

- [Run agents with Linear](https://getrush.ai/integrations/linear.md)
- [Run agents with Sentry](https://getrush.ai/integrations/sentry.md)
- [Run agents with Slack](https://getrush.ai/integrations/slack.md)
- [Run agents with Datadog](https://getrush.ai/integrations/datadog.md)
- [40 more apps and MCP servers Rush connects to](https://getrush.ai/integrations.md)
- [Hand work to Rush from any MCP client](https://getrush.ai/docs/concepts/mcp-server.md)

### Run it on Rush

- [Fix Sentry Errors in a Next.js App](https://getrush.ai/run/fix-sentry-errors/nextjs.md)
- [Add Rate Limiting to an Express API from a Linear Issue](https://getrush.ai/run/add-rate-limiting/express.md)
- [Add OpenTelemetry Tracing to a Go Service](https://getrush.ai/run/add-opentelemetry/go.md)
- [Write Unit Tests for a Node.js App](https://getrush.ai/run/write-unit-tests/nodejs.md)

## Sources

1. Rush, "Rush product requirements", retrieved 2026-09-15. https://getrush.ai/cloud
2. Cognition, "Devin's 2025 Performance Review", published 2025-11-14. https://cognition.com/blog/devin-annual-performance-review-2025
3. Cursor, "Self-hosted machines for Cloud Agents", published 2026-09-02. https://cursor.com/blog/self-hosted-machines
4. GitHub Docs, "About GitHub Copilot cloud agent", retrieved 2026-09-15. https://docs.github.com/en/copilot/concepts/agents/cloud-agent/about-cloud-agent
5. Anthropic Docs, "Use Claude Code on the web", retrieved 2026-09-15. https://code.claude.com/docs/en/claude-code-on-the-web
6. OpenAI / ChatGPT Learn, "Codex cloud", retrieved 2026-09-15. https://learn.chatgpt.com/docs/cloud
7. Start Debugging, "Claude Code vs Cursor vs Copilot Agent Mode: Where Each Wins in 2026", published 2026-06-03. https://startdebugging.net/2026/06/claude-code-vs-cursor-vs-copilot-agent-mode-where-each-wins/
