Alternatives · Cloud agents · verified 15 Sep 2026
Amp orbs alternatives
Teams look past Amp orbs when they want a pull request by default, a burst above 20 metered orbs, or an agent other than Amp.
Facts checked 15 September 2026. Prices and limits move. Read the citations.
Rush is our product and is listed first. Every other row is from the vendor's own pages, retrieved on the date beside it.
Read this first
The useful distinction
Teams look past Amp orbs when they want a pull request by default, a burst above 20 metered orbs, or an agent other than Amp.
The useful split is who builds the agent. Most products here run their own. Rush runs Claude Code, Codex or OpenCode, the vendors' own CLIs, and returns the result with the record of how it was made.
Routing
If you… use… not if
| If you | Use | Not if |
|---|---|---|
| You want to send a task by API or MCP and get back a pull request, report or files with the transcript. | Rush | You need to self-host, use GitLab or Bitbucket, or bring an agent loop of your own. |
| You want Factory's Droid across terminal, IDE, browser and Slack, with a computer that stays awake. | Factory Droids | You need published rate limits, or managed computers below $100 a month. |
| Your team is standardized on Cursor and wants the same Agent off the laptop. | Cursor Cloud Agents | You will not put the repository on a paid Cursor plan. |
| You only run Claude Code and want Anthropic to host the VM inside your Claude plan. | Claude Code on the web | You need Codex or OpenCode too, or your org has Zero Data Retention. |
| You are on ChatGPT and want OpenAI's agent in a box, included in the plan. | Codex cloud | You call Codex with an API key: that path has no cloud. |
| You want Cognition's own agent on tickets, with Slack, Linear and Jira wiring and stacked GitHub pull requests. | Devin | You must bring your own model keys; Devin does not support them. |
| You already live in the Warp terminal and want the same agents in the cloud from Slack, Linear or GitHub Actions. | Warp Oz | You need published concurrency on a self-serve plan. |
Landscape
The field
Prices and limits from vendor pages retrieved 15 September 2026. Check the source before you buy.
| 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 5 agent-hours / month, then $20 Pro | Three harnesses. GitHub repos only. No self-host. |
| 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. |
| 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. |
| 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. |
| 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. |
| 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. |
| Warp Oz | Cloud agents from the Warp terminal company | Warp Agent, Claude Code, Codex | Docker-based sandbox per run | PR on GitHub | Free limited; Build $20 / mo | Self-host on Enterprise. Concurrency TBD. |
Depth
In depth
Pro $20 / month; managed Droid Computers start at Plus $100 / month. Checked 15 September 2026.
Factory Droids
You want Factory's Droid across terminal, IDE, browser and Slack, with a computer that stays awake.
Factory's own coding agents across terminal, IDE, browser, and Slack. Persistent Droid Computers keep the machine awake between sessions.
Product page: one prompt to PR. Slack integration can open a PR and handle CI via a subagent.
Taps out. Managed computers are a Plus+ feature. Rate limits are unpublished. Remote Slack delegations are private preview.
Pro $20 / month; Teams Standard $40 / user / month. Checked 15 September 2026.
Cursor Cloud Agents
Your team is standardized on Cursor and wants the same Agent off the laptop.
Cursor's local Agent, moved into isolated cloud VMs. Formerly called Background Agents. Available on paid Cursor plans.
Works on a separate branch and opens a draft PR. GitHub, GitLab, Azure DevOps, Bitbucket Cloud.
Taps out. Requires a paid Cursor plan and an environment snapshot. Multi-repo long-running is not available. Move-to-cloud drops uncommitted files. Prompt-injection risk is documented because commands auto-run.
Claude Pro $20 / month; Max 5x $100 / month. Checked 15 September 2026.
Claude Code on the web
You only run Claude Code and want Anthropic to host the VM inside your Claude plan.
The same Claude Code harness, hosted on Anthropic VMs. Connect GitHub, submit a task, review the PR. Status: research preview.
Clones a GitHub repo, pushes a branch, opens a PR from the web UI. GitLab/Bitbucket are bundle-only and cannot push back.
Taps out. Research preview. GitHub required to push. Zero Data Retention orgs cannot use cloud sessions. IP allowlists break Anthropic-hosted runs. Claude-only.
ChatGPT Plus $20 / month; Pro 5x $100 / month; Free includes limited Codex. Checked 15 September 2026.
Codex cloud
You are on ChatGPT and want OpenAI's agent in a box, included in the plan.
OpenAI's coding agent, running background tasks in isolated ChatGPT cloud environments. Included with ChatGPT plans. Not the 2021 Codex model.
Connect GitHub or GitLab (Beta). Review the summary and diff, then open a PR. @codex on issues and PRs.
Taps out. API-key path has no cloud, GitHub review, or Slack. Agent internet is off by default. Cloud chats can cost more than local.
Pro $20 / month; Teams $80 minimum + $40 / full seat. Checked 15 September 2026.
Devin
You want Cognition's own agent on tickets, with Slack, Linear and Jira wiring and stacked GitHub pull requests.
Cognition's own autonomous software engineer. It plans, writes, tests, and ships in a cloud Devbox. The Brain always stays in Cognition's cloud.
Creates PRs on GitHub, GitLab, Bitbucket, or Azure DevOps. Stacked PRs on GitHub.com only.
Taps out. You cannot bring your own model keys. Ambiguous senior-scope work is out of scope by Cognition's own 2025 review. Quotas are opaque.
Free with limited cloud agents; Build $20 / month with $20 of usage at API rates; Business $50 / user / month. Checked 17 October 2026.
Warp Oz
You already live in the Warp terminal and want the same agents in the cloud from Slack, Linear or GitHub Actions.
Warp's cloud agent platform. It starts Warp Agent, Claude Code or Codex runs from a CLI, an API, Slack, Linear or GitHub Actions, in Docker-based sandboxes on Warp or your own compute.
Pushes branches and opens pull requests on GitHub, authored by the Warp Factories GitHub App with team authorization.
Taps out. Free has limited cloud agents. Self-hosted execution is Enterprise only. Build-plan concurrency is still being finalized. GitHub is the only documented forge.
Rush
What Rush is
Rush is the Amp orbs alternative when the agent should be one of the vendors' own CLIs and the pull request should come without an AGENTS.md instruction.
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
What is the best Amp orbs alternative?
It depends on the part of the job you want to keep. Use Factory Droids if you want Factory's Droid across terminal, IDE, browser and Slack, with a computer that stays awake. Use Cursor Cloud Agents if your team is standardized on Cursor and wants the same Agent off the laptop. Use Claude Code on the web if you only run Claude Code and want Anthropic to host the VM inside your Claude plan. Use Rush if you want to send a task by API or MCP and get back a pull request, report or files with the transcript.
Can I move from Amp orbs to Rush?
Yes. The steps, from Amp Inc.'s own docs, are on the Migrate from Amp orbs to Rush page. Code you already pushed stays where it is.
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.
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] 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] Amp, “Orbs Overview | Amp Docs”, retrieved 2026-09-15. https://ampcode.com/docs/orbs
- [9] Amp, “Pricing - Amp”, retrieved 2026-09-15. https://ampcode.com/pricing
- [10] Amp, “Sizes & Costs | Amp Docs”, retrieved 2026-09-15. https://ampcode.com/docs/orbs/sizes-and-costs
- [11] Amp, “GitHub & Git | Amp Docs”, retrieved 2026-09-15. https://ampcode.com/docs/github
- [12] Factory, “Factory Droids | AI Coding Agents”, retrieved 2026-09-15. https://factory.ai/product/droids
- [13] Factory, “Factory Pricing”, retrieved 2026-09-15. https://factory.ai/pricing
- [14] Factory Docs, “Droid Computers”, retrieved 2026-09-15. https://docs.factory.ai/droid-computers/overview
- [15] Factory Docs, “Model Context Protocol (MCP)”, retrieved 2026-09-15. https://docs.factory.ai/harness/mcp
- [16] Cursor Docs, “Cloud Agents”, retrieved 2026-09-15. https://cursor.com/docs/cloud-agent
- [17] Cursor, “Cursor · Pricing”, retrieved 2026-09-15. https://cursor.com/pricing
- [18] Cursor Docs, “Models & Pricing”, retrieved 2026-09-15. https://cursor.com/docs/models-and-pricing
- [19] Cursor Docs, “Cloud Agent security”, retrieved 2026-09-15. https://cursor.com/docs/cloud-agent/security
- [20] Cursor Docs, “Cloud Agent capabilities”, retrieved 2026-09-15. https://cursor.com/docs/cloud-agent/capabilities
- [21] Cursor, “New Coding Model and Agent Interface · Cursor 2.0”, published 2025-10-29. https://cursor.com/changelog/2-0
- [22] Anthropic Docs, “Use Claude Code on the web”, retrieved 2026-09-15. https://code.claude.com/docs/en/claude-code-on-the-web
- [23] Anthropic, “Claude Code on the web”, published 2025-10-20. https://www.anthropic.com/news/claude-code-on-the-web
- [24] Anthropic, “Plans & Pricing | Claude”, retrieved 2026-09-15. https://claude.com/pricing
- [25] Anthropic, “Claude Code by Anthropic”, retrieved 2026-09-15. https://claude.com/product/claude-code
- [26] OpenAI / ChatGPT Learn, “Codex cloud”, retrieved 2026-09-15. https://learn.chatgpt.com/docs/cloud
- [27] OpenAI / ChatGPT Learn, “Cloud environments”, retrieved 2026-09-15. https://learn.chatgpt.com/docs/environments/cloud-environment.md
- [28] OpenAI, “Pricing | ChatGPT Learn”, retrieved 2026-09-15. https://learn.chatgpt.com/docs/pricing
- [29] 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/
- [30] Cognition, “Devin | The AI Software Engineer”, retrieved 2026-09-15. https://devin.ai/
- [31] Cognition, “Plans and Pricing | Devin”, retrieved 2026-09-15. https://devin.ai/pricing
- [32] Cognition Docs, “Introducing Devin”, retrieved 2026-09-15. https://docs.devin.ai/get-started/devin-intro
- [33] Cognition Docs, “Self-serve plans”, retrieved 2026-09-15. https://docs.devin.ai/admin/billing/self-serve
- [34] Cognition Docs, “Enterprise Deployment”, retrieved 2026-09-15. https://docs.devin.ai/enterprise/deployment/overview
- [35] Cognition Docs, “Devin GitHub integration”, retrieved 2026-09-15. https://docs.devin.ai/integrations/gh
- [36] Cognition Docs, “Devin MCP servers and marketplace”, retrieved 2026-09-15. https://docs.devin.ai/work-with-devin/mcp
- [37] Cognition, “New self-serve plans for Devin”, published 2026-04-14. https://cognition.com/blog/new-self-serve-plans-for-devin
- [38] Cognition, “Privacy Policy”, published 2026-03-09. https://cognition.com/legal/privacy-policy
- [39] Warp, “Pricing”, retrieved 2026-10-17. https://www.warp.dev/pricing
- [40] Warp, “Oz Cloud Agent Platform: Every agent at your command”, retrieved 2026-10-17. https://www.warp.dev/oz
- [41] Warp, “Automation Platform (docs)”, retrieved 2026-10-17. https://docs.warp.dev/_llms-txt/automation-platform.txt
- [42] Warp, “Warp Platform API 1.0.0 (OpenAPI)”, retrieved 2026-10-17. https://docs.warp.dev/openapi.json
Next
Run the next Task on Rush
Connect a repository. Pick Claude Code, Codex, or OpenCode. Review the PR.