Compare · Cloud agents · verified 15 Sep 2026

OpenHands Cloud vs Devin

Both take an issue into a cloud sandbox and open a pull request. OpenHands is open source and can run Claude Code or Codex; Devin is Cognition's own agent.

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 OpenHands for open source, self-hosting and your own model key. Pick Devin for Cognition's agent with Slack, Linear and Jira wiring.

Read this first

The useful distinction

OpenHands Cloud: the hosted version of OpenHands, an MIT-licensed coding agent platform. It works on GitHub, GitLab or Bitbucket repositories, and in the cloud also runs Claude Code, Codex and Gemini CLI.

Devin: Cognition's own autonomous software engineer. It plans, writes, tests, and ships in a cloud Devbox. The Brain always stays in Cognition's cloud.

Head to head

Buyer questions

QuestionOpenHands CloudDevin
What runsThe OpenHands agent, or Claude Code, Codex and Gemini CLI over ACP with your own token or key.Cognition's compound agent. Third-party LLM API keys are not supported.
IsolationSandboxed runtime per conversation. The docs describe Docker and remote sandboxes; which one Cloud uses is not stated.One isolated VM (Devbox) per session. Snapshot boots; session changes do not write back. Outposts can run execution on customer machines; the Brain stays at Cognition.
Result and pull requestOpens a pull request when it decides the issue is resolved, from an @openhands comment or an openhands label. GitHub, GitLab and Bitbucket; Azure DevOps on Enterprise.Creates PRs on GitHub, GitLab, Bitbucket, or Azure DevOps. Stacked PRs on GitHub.com only.
MCPMCP client over SSE, Streamable HTTP and stdio, including OAuth servers. Cloud keeps the OAuth credential.stdio, SSE, and HTTP MCP client, plus an official Devin MCP server at mcp.devin.ai.
TeamSlack and Jira Cloud. Enterprise adds SAML, RBAC, audit logs and Jira Data Center.Session UI with shell, IDE, and browser. Slack and Teams. Linear and Jira ticket triggers. Invite-team on Team and Enterprise.
Starting priceIndividual SaaS free with your own key or their models at cost; Enterprise customPro $20 / month; Teams $80 minimum + $40 / full seat
Where it taps outOlder conversations pause to cap concurrency. A pull request mention works only on repositories added in the UI. Free is one user and 10 conversations a day. The GitHub token expires after 8 hours.You cannot bring your own model keys. Ambiguous senior-scope work is out of scope by Cognition's own 2025 review. Quotas are opaque.

Decision

When each side wins

OpenHands Cloud wins when

  • You want the agent to be open source (MIT) and able to run in your own VPC.
  • Your repositories are on GitLab or Bitbucket as well as GitHub.
  • You bring your own model key at no markup.

Devin wins when

  • You want Cognition's agent with Slack, Teams, Linear and Jira triggers built in.
  • You need pull requests on GitHub, GitLab, Bitbucket or Azure DevOps, and stacked pull requests on GitHub.
  • You need Enterprise dedicated VPC or Outposts that run execution on your machines.

Rush

Where Rush sits

Rush shares OpenHands' answer to which agent: Claude Code, Codex or OpenCode. It adds a self-serve team plan and a session API that returns proof.

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 OpenHands Cloud cheaper than Devin?

List prices, read off each vendor's pricing page on 15 September 2026. OpenHands Cloud: Individual SaaS free with your own key or their models at cost; Enterprise custom. Devin: Pro $20 / month; Teams $80 minimum + $40 / full seat. The units differ, so price the job you run, not the plan.

Where does Rush fit next to OpenHands Cloud and Devin?

Rush shares OpenHands' answer to which agent: Claude Code, Codex or OpenCode. It adds a self-serve team plan and a session API that returns proof.

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] All Hands AI, “OpenHands Pricing”, retrieved 2026-10-17. https://www.openhands.dev/pricing
  2. [2] All Hands AI, “Getting Started”, retrieved 2026-10-17. https://docs.openhands.dev/openhands/usage/cloud/openhands-cloud.md
  3. [3] All Hands AI, “Cloud API Overview”, retrieved 2026-10-17. https://docs.openhands.dev/openhands/usage/cloud/cloud-api.md
  4. [4] All Hands AI, “ACP Agents”, retrieved 2026-10-17. https://docs.openhands.dev/openhands/usage/agent-canvas/acp-agents.md
  5. [5] All Hands AI, “GitHub Integration”, retrieved 2026-10-17. https://docs.openhands.dev/openhands/usage/cloud/github-installation.md
  6. [6] All Hands AI, “Model Context Protocol (MCP) settings”, retrieved 2026-10-17. https://docs.openhands.dev/openhands/usage/settings/mcp-settings.md
  7. [7] All Hands AI, “docs index (llms.txt)”, retrieved 2026-10-17. https://docs.openhands.dev/llms.txt
  8. [8] Cognition, “Devin | The AI Software Engineer”, retrieved 2026-09-15. https://devin.ai/
  9. [9] Cognition, “Plans and Pricing | Devin”, retrieved 2026-09-15. https://devin.ai/pricing
  10. [10] Cognition Docs, “Introducing Devin”, retrieved 2026-09-15. https://docs.devin.ai/get-started/devin-intro
  11. [11] Cognition Docs, “Self-serve plans”, retrieved 2026-09-15. https://docs.devin.ai/admin/billing/self-serve
  12. [12] Cognition Docs, “Enterprise Deployment”, retrieved 2026-09-15. https://docs.devin.ai/enterprise/deployment/overview
  13. [13] Cognition Docs, “Devin GitHub integration”, retrieved 2026-09-15. https://docs.devin.ai/integrations/gh
  14. [14] Cognition Docs, “Devin MCP servers and marketplace”, retrieved 2026-09-15. https://docs.devin.ai/work-with-devin/mcp
  15. [15] Cognition, “New self-serve plans for Devin”, published 2026-04-14. https://cognition.com/blog/new-self-serve-plans-for-devin
  16. [16] Cognition, “Privacy Policy”, published 2026-03-09. https://cognition.com/legal/privacy-policy
  17. [17] Rush, “Rush product requirements”, retrieved 2026-09-15. https://getrush.ai/cloud
  18. [18] Rush, “Rush pricing (live contract on getrush.ai)”, retrieved 2026-09-15. https://getrush.ai/pricing
  19. [19] Rush, “Isolation, plainly”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/isolation
  20. [20] Rush, “Results and proof”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/results-and-proof
  21. [21] Rush, “Usage and billing”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/usage-and-billing
  22. [22] Rush, “Rush MCP server”, retrieved 2026-10-17. https://getrush.ai/docs/concepts/mcp-server
  23. [23] 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