# Rush vs CodeRabbit

CodeRabbit reads the diff and comments. A Rush review run checks out the branch in its own sandbox, can run the tests, and comments with the transcript behind it.

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

**The short answer.** Pick CodeRabbit for line-by-line review on every forge. Pick Rush when the reviewer should run the code, or when review is one job among several you hand an agent.

## The useful distinction

CodeRabbit: an AI code reviewer that posts pull request summaries and line comments on GitHub, GitLab, Azure DevOps and Bitbucket, learns from your team's replies, and can push fixes.

A review bot reads the diff and comments. An agent in a sandbox can also check out the branch, run the tests and push a fix. Both are useful; they are different jobs.

## Buyer questions

| Question | Rush | CodeRabbit |
| --- | --- | --- |
| What runs | Claude Code, Codex or OpenCode, the vendors' own CLIs, or a saved agent built on one. | Models from OpenAI and Anthropic. Reviews can run shell commands and static analysis; coding tasks run in a sandbox that is in beta. |
| Isolation | One 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. | Hosted by CodeRabbit; customer code is not used for training. Self-hosting needs Enterprise with 500 or more seats. |
| Result and pull request | A 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. | Comments on every pull request. Fix comments pushes a commit to the branch or opens a stacked pull request, on Essentials and up. |
| MCP | Rush is an MCP server at api.prix.dev/mcp with 18 tools. A run also takes MCP servers by connection or inline. | MCP client only: it pulls context from MCP servers you add in its web UI (5 to 20 by plan). |
| Team | Everyone in the org sees the same Projects and runs, with who started each. Automations start runs from GitHub events, schedules, webhooks and Linear. | Jira and Linear, Slack, a .coderabbit.yaml in the repository, and Learnings from chat replies. Reads AGENTS.md and CLAUDE.md as review guidelines by default. |
| Starting price | Free 5 agent-hours / month; Pro $20; Team $200 | Free on public repositories; Essentials $24 / developer / month billed annually ($30 monthly) |
| Where it taps out | Three harnesses. Repositories through the GitHub App only. No self-host or customer VPC. A key runs 4 at once by default, up to 100. | Hourly review caps and $0.25 per reviewed file past the allowance. Self-hosting from 500 seats. Fix comments stops on merge conflicts. Its docs do not say reviews run your tests. |

## When each side wins

### Rush wins when

- The reviewer should run the tests in its own sandbox and say what it ran, not only read the diff.
- Review is one of many jobs: the same Rush plan fixes a failing CI run or writes the tests.
- You are billed for sandbox time, not per seat or per reviewed file.

### CodeRabbit wins when

- Your repositories are on GitLab, Azure DevOps or Bitbucket, including self-managed versions.
- You want a mature line-comment UX that learns from your replies.
- Your open-source project wants free reviews forever.

## Where Rush sits

A Rush review is an automation: a pull_request.opened trigger starts a read-only run that reads the repository and comments, but cannot push. The agent is Claude Code, Codex or OpenCode, and its sandbox can run your tests first.

## 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

### Does CodeRabbit run my tests?

CodeRabbit's FAQ says reviews can execute shell commands and deep static analysis, and coding tasks run in a sandbox marked beta. Its docs retrieved 17 October 2026 do not say that reviews run your test suite.

### Can I move from CodeRabbit to Rush?

Yes. The steps, from CodeRabbit's own docs, are on the Migrate from CodeRabbit 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.

## Keep reading

- [CodeRabbit alternatives](https://getrush.ai/compare/coderabbit-alternatives.md)
- [Migrate from CodeRabbit to Rush](https://getrush.ai/compare/migrate-from-coderabbit.md)
- [CodeRabbit vs Greptile](https://getrush.ai/compare/coderabbit-vs-greptile.md)
- [CodeRabbit vs Graphite](https://getrush.ai/compare/coderabbit-vs-graphite.md)
- [CodeRabbit vs Qodo](https://getrush.ai/compare/coderabbit-vs-qodo.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. CodeRabbit, "CodeRabbit Pricing", retrieved 2026-10-17. https://www.coderabbit.ai/pricing
9. CodeRabbit, "CodeRabbit FAQs", retrieved 2026-10-17. https://docs.coderabbit.ai/faq.md
10. CodeRabbit, "CodeRabbit docs home", retrieved 2026-10-17. https://docs.coderabbit.ai/
11. CodeRabbit, "Coding environments", retrieved 2026-10-17. https://docs.coderabbit.ai/code/environments.md
12. CodeRabbit, "Self-hosted CodeRabbit", retrieved 2026-10-17. https://docs.coderabbit.ai/self-hosted/overview.md
13. CodeRabbit, "Fix comments", retrieved 2026-10-17. https://docs.coderabbit.ai/finishing-touches/autofix.md
14. CodeRabbit, "MCP Servers", retrieved 2026-10-17. https://docs.coderabbit.ai/knowledge-base/mcp-context.md
15. CodeRabbit, "Code guidelines", retrieved 2026-10-17. https://docs.coderabbit.ai/knowledge-base/code-guidelines.md