Compare · Cloud agents · verified 15 Sep 2026

Codex cloud vs Google Jules

OpenAI's and Google's asynchronous coding agents. Both clone a repository into a cloud machine and propose a pull request.

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

Start a TaskAll comparison pages
Vendor agentDevin · Cursor · Copilot · Julessame jobRushYour harness, isolated, one PR
Cloud agent loop from request to pull request

Neither product is ours. Rush is, and it gets one paragraph below. Every cell is from the vendor's own pages.

The short answer

Pick Codex cloud if you are on ChatGPT and want GitLab in beta. Pick Jules for 15 free Gemini tasks a day on GitHub.

Read this first

The useful distinction

Codex cloud: OpenAI's coding agent, running background tasks in isolated ChatGPT cloud environments. Included with ChatGPT plans. Not the 2021 Codex model.

Google Jules: an asynchronous coding agent that clones a GitHub repo into a short-lived Cloud VM, proposes a plan, and can open a PR.

Head to head

Buyer questions

QuestionCodex cloudGoogle Jules
What runsCodex agent. AGENTS.md for lint/test/review rules.Jules, powered by Gemini (2.5 Pro on free; 3 Pro on paid, per Jules docs).
IsolationIsolated OpenAI-managed containers. Setup has network and secrets; agent phase is offline by default and secrets are removed first.Fresh Ubuntu VM per task, internet on, snapshot optional. Preinstalled Node, Python, Go, Java, Rust, Docker.
Result and pull requestConnect GitHub or GitLab (Beta). Review the summary and diff, then open a PR. @codex on issues and PRs.GitHub App only. Issue label jules, or API AUTO_CREATE_PR. Other forges are future work.
MCPOfficial MCP config is documented for desktop, CLI, and IDE. Whether cloud containers load config.toml MCP servers is not documented.Hand-selected allowlist (Linear, Stitch, Neon, Tinybird, Context7, Supabase as of 2 Feb 2026). Arbitrary MCP is intentionally limited.
TeamParallel cloud chats. Slack and Linear. Workspace-shared environments on team plans.Web app. Browser notifications. API intended for Slack/Linear/GitHub embeds. Paid plans are individual accounts.
Starting priceChatGPT Plus $20 / month; Pro 5x $100 / month; Free includes limited Codex15 tasks / day free; 100 / day on Google AI Pro; 300 / day on Ultra ($99.99 / month US)
Where it taps outAPI-key path has no cloud, GitHub review, or Slack. Agent internet is off by default. Cloud chats can cost more than local.GitHub only. No Workspace/enterprise upgrade path yet. Capacity is not guaranteed. English official. 18+.

Decision

When each side wins

Codex cloud wins when

  • You already pay for ChatGPT, and cloud tasks come with the plan.
  • You want the agent offline during its work phase, with secrets removed first.
  • You want @codex on GitHub issues and pull requests, and GitLab in beta.

Google Jules wins when

  • You want 15 tasks a day free.
  • You want a fresh VM with Node, Python, Go, Java, Rust and Docker preinstalled.
  • You want Gemini as the model.

Rush

Where Rush sits

Rush runs Codex from an API for a team. It does not run Jules or Gemini.

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

Is Codex cloud cheaper than Google Jules?

List prices, read off each vendor's pricing page on 15 September 2026. Codex cloud: ChatGPT Plus $20 / month; Pro 5x $100 / month; Free includes limited Codex. Google Jules: 15 tasks / day free; 100 / day on Google AI Pro; 300 / day on Ultra ($99.99 / month US). The units differ, so price the job you run, not the plan.

Where does Rush fit next to Codex cloud and Google Jules?

Rush runs Codex from an API for a team. It does not run Jules or Gemini.

Cluster

Keep reading

Citations

Sources

Every factual claim on this page traces to one of these URLs. Retrieval date is 15 September 2026 unless the source prints an earlier published date.

  1. [1] OpenAI / ChatGPT Learn, “Codex cloud”, retrieved 2026-09-15. https://learn.chatgpt.com/docs/cloud
  2. [2] OpenAI / ChatGPT Learn, “Cloud environments”, retrieved 2026-09-15. https://learn.chatgpt.com/docs/environments/cloud-environment.md
  3. [3] OpenAI, “Pricing | ChatGPT Learn”, retrieved 2026-09-15. https://learn.chatgpt.com/docs/pricing
  4. [4] TechCrunch, “OpenAI launches Codex, an AI coding agent, in ChatGPT”, published 2025-05-16. https://techcrunch.com/2025/05/16/openai-launches-codex-an-ai-coding-agent-in-chatgpt/
  5. [5] Google, “Jules - An Autonomous Coding Agent”, retrieved 2026-09-15. https://jules.google/
  6. [6] Google, “Limits and Plans | Jules”, retrieved 2026-09-15. https://jules.google/docs/usage-limits/
  7. [7] Google, “FAQ | Jules”, retrieved 2026-09-15. https://jules.google/docs/faq/
  8. [8] Google, “Environment setup | Jules”, retrieved 2026-09-15. https://jules.google/docs/environment/
  9. [9] Rush, “Rush product requirements”, retrieved 2026-09-15. https://getrush.ai/cloud
  10. [10] Rush, “Rush pricing (live contract on getrush.ai)”, retrieved 2026-09-15. https://getrush.ai/pricing
  11. [11] Rush, “Isolation, plainly”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/isolation
  12. [12] Rush, “Results and proof”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/results-and-proof
  13. [13] Rush, “Usage and billing”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/usage-and-billing
  14. [14] Rush, “Rush MCP server”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/mcp-server
  15. [15] Rush, “Automations”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/automations

Next

Run the next Task on Rush

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

How the runtime works