# Factory Droids alternatives

Teams look past Factory Droids when the rolling rate limits are unpublished, or when managed computers start at the $100 Plus plan.

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.

## The useful distinction

Teams look past Factory Droids when the rolling rate limits are unpublished, or when managed computers start at the $100 Plus plan.

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.

## What Rush is

Rush is the alternative for teams that like Factory's persistent machines and want the agent to be Claude Code, Codex or OpenCode instead of Droid.

## 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 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. |
| 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 use Amp and want threads that keep running on a remote machine, with multiplayer prompting. | Amp orbs | You want the pull request opened by default rather than by an AGENTS.md instruction. |
| You want Augment's Context Engine and SOC 2 Type II on every plan, with GitLab or Teams in the loop. | Augment Cloud Agents | You want Claude Code or Codex itself as the cloud agent, on your own account. |
| You want more harnesses than three, three forges and Sentry or PagerDuty triggers. | Tembo | You want a free plan with included hours, or webhooks when a run finishes. |
| You want an open-source agent you can also self-host, on GitHub, GitLab or Bitbucket. | OpenHands Cloud | You need a team plan without an Enterprise contract. |

## 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 5 agent-hours / month, then $20 Pro | Three harnesses. GitHub repos only. No self-host. |
| 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. |
| 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. |
| 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. |
| Augment Cloud Agents | Augment's agent on tickets, in a cloud VM | Auggie | Fresh VM per session | PR on GitHub or GitLab | Standard $20 / mo flat; Business $100 | 40% fee on model usage. No free tier. |
| Tembo | Run many coding CLIs on events, in cloud VMs | Claude Code, Codex, Cursor, OpenCode, Amp, Pi | Dedicated VM per session | PR on GitHub, GitLab or Bitbucket | Pro $60 / mo with $60 usage; Max $200 | Pro 5 users. No API webhooks. |
| OpenHands Cloud | Open-source coding agent, hosted | OpenHands, Claude Code, Codex, Gemini CLI | Sandbox per conversation | PR on GitHub, GitLab or Bitbucket | Individual free; Enterprise custom | Free is 1 user, 10 conversations / day. |

## In depth

### Devin

Pro $20 / month; Teams $80 minimum + $40 / full seat. Checked 15 September 2026.. 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.

### Cursor Cloud Agents

Pro $20 / month; Teams Standard $40 / user / month. Checked 15 September 2026.. 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.

### Amp orbs

Hobby free (pay-as-you-go orbs); Individual $20 / month includes 45,000 orb minutes. Checked 15 September 2026.. You use Amp and want threads that keep running on a remote machine, with multiplayer prompting.

Amp's frontier agent on remote machines (orbs) that keep working when the laptop is closed. Separate company from Sourcegraph as of 2 Dec 2025.

GitHub App acts as you. gh is preinstalled. Docs tell you to put gh pr create in AGENTS.md for automatic PRs. GitHub Enterprise Server is not supported.

**Taps out.** Burst limit of 20 metered orbs. Multiplayer exposes secrets and the terminal to the workspace. GHES unsupported.

### Augment Cloud Agents

Standard $20 / month flat, up to 50 seats, $20 usage included; Business $100 / month. Checked 17 October 2026.. You want Augment's Context Engine and SOC 2 Type II on every plan, with GitLab or Teams in the loop.

Augment's cloud agents (Cosmos) take tickets, reviews and fixes from GitHub, GitLab, Jira, Linear and Slack, work in fresh sandboxed VMs with Augment's Context Engine, and open pull requests.

Opens pull requests on GitHub, GitHub Enterprise Server, GitLab Cloud and self-hosted GitLab.

**Taps out.** No free tier. A 40% fee on model usage. Self-serve plans cap at 50 seats and 50 concurrent sessions. A running session does not pick up environment updates.

### Tembo

Free trial; Pro $60 / month with $60 of usage, up to 5 users; Max $200 / month. Checked 17 October 2026.. You want more harnesses than three, three forges and Sentry or PagerDuty triggers.

An agent orchestration platform that runs Claude Code, Codex, Cursor, Amp, OpenCode or Pi in a dedicated cloud VM per session, from GitHub, Linear, Jira, Slack, Sentry or PagerDuty events, and opens pull requests.

Opens pull requests on GitHub, GitLab and Bitbucket, including coordinated pull requests across repositories.

**Taps out.** Pro caps at 5 users and medium sandboxes. Sandboxes are destroyed after the session. The API documents no webhooks. API keys expire after 90 days by default.

### OpenHands Cloud

Individual SaaS free with your own key or their models at cost; Enterprise custom. Checked 17 October 2026.. You want an open-source agent you can also self-host, on GitHub, GitLab or Bitbucket.

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.

Opens 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.

**Taps out.** Older 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.

## 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

### What is the best Factory Droids alternative?

It depends on the part of the job you want to keep. Use Devin if you want Cognition's own agent on tickets, with Slack, Linear and Jira wiring and stacked GitHub pull requests. Use Cursor Cloud Agents if your team is standardized on Cursor and wants the same Agent off the laptop. Use Amp orbs if you use Amp and want threads that keep running on a remote machine, with multiplayer prompting. 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 Factory Droids to Rush?

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

## Keep reading

- [Rush vs Factory Droids](https://getrush.ai/compare/rush-vs-factory-droids.md)
- [Migrate from Factory Droids to Rush](https://getrush.ai/compare/migrate-from-factory-droids.md)
- [Rush vs Devin](https://getrush.ai/compare/rush-vs-devin.md)
- [Rush vs Cursor Cloud Agents](https://getrush.ai/compare/rush-vs-cursor-cloud-agents.md)
- [Rush vs Amp orbs](https://getrush.ai/compare/rush-vs-amp.md)
- [Rush vs Augment Cloud Agents](https://getrush.ai/compare/rush-vs-augment-cloud-agents.md)
- [Rush vs Tembo](https://getrush.ai/compare/rush-vs-tembo.md)
- [Rush vs OpenHands Cloud](https://getrush.ai/compare/rush-vs-openhands.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. Factory, "Factory Droids | AI Coding Agents", retrieved 2026-09-15. https://factory.ai/product/droids
9. Factory, "Factory Pricing", retrieved 2026-09-15. https://factory.ai/pricing
10. Factory Docs, "Droid Computers", retrieved 2026-09-15. https://docs.factory.ai/droid-computers/overview
11. Factory Docs, "Model Context Protocol (MCP)", retrieved 2026-09-15. https://docs.factory.ai/harness/mcp
12. Cognition, "Devin | The AI Software Engineer", retrieved 2026-09-15. https://devin.ai/
13. Cognition, "Plans and Pricing | Devin", retrieved 2026-09-15. https://devin.ai/pricing
14. Cognition Docs, "Introducing Devin", retrieved 2026-09-15. https://docs.devin.ai/get-started/devin-intro
15. Cognition Docs, "Self-serve plans", retrieved 2026-09-15. https://docs.devin.ai/admin/billing/self-serve
16. Cognition Docs, "Enterprise Deployment", retrieved 2026-09-15. https://docs.devin.ai/enterprise/deployment/overview
17. Cognition Docs, "Devin GitHub integration", retrieved 2026-09-15. https://docs.devin.ai/integrations/gh
18. Cognition Docs, "Devin MCP servers and marketplace", retrieved 2026-09-15. https://docs.devin.ai/work-with-devin/mcp
19. Cognition, "New self-serve plans for Devin", published 2026-04-14. https://cognition.com/blog/new-self-serve-plans-for-devin
20. Cognition, "Privacy Policy", published 2026-03-09. https://cognition.com/legal/privacy-policy
21. Cursor Docs, "Cloud Agents", retrieved 2026-09-15. https://cursor.com/docs/cloud-agent
22. Cursor, "Cursor · Pricing", retrieved 2026-09-15. https://cursor.com/pricing
23. Cursor Docs, "Models & Pricing", retrieved 2026-09-15. https://cursor.com/docs/models-and-pricing
24. Cursor Docs, "Cloud Agent security", retrieved 2026-09-15. https://cursor.com/docs/cloud-agent/security
25. Cursor Docs, "Cloud Agent capabilities", retrieved 2026-09-15. https://cursor.com/docs/cloud-agent/capabilities
26. Cursor, "New Coding Model and Agent Interface · Cursor 2.0", published 2025-10-29. https://cursor.com/changelog/2-0
27. Amp, "Orbs Overview | Amp Docs", retrieved 2026-09-15. https://ampcode.com/docs/orbs
28. Amp, "Pricing - Amp", retrieved 2026-09-15. https://ampcode.com/pricing
29. Amp, "Sizes & Costs | Amp Docs", retrieved 2026-09-15. https://ampcode.com/docs/orbs/sizes-and-costs
30. Amp, "GitHub & Git | Amp Docs", retrieved 2026-09-15. https://ampcode.com/docs/github
31. Augment Code, "Augment Code Pricing - Standard, Business, and Enterprise Plans", retrieved 2026-10-17. https://www.augmentcode.com/pricing
32. Augment Code, "Cloud Agents: Run Your Cloud Agents", retrieved 2026-10-17. https://www.augmentcode.com/product/cloud-agents
33. Augment Code, "Token-Based Pricing", retrieved 2026-10-17. https://docs.augmentcode.com/models/token-based-pricing.md
34. Augment Code, "Cloud Environments", retrieved 2026-10-17. https://docs.augmentcode.com/cosmos/environments/cloud.md
35. Augment Code, "Cosmos Environments", retrieved 2026-10-17. https://docs.augmentcode.com/cosmos/environments/overview.md
36. Augment Code, "Managing Cosmos with auggie cloud", retrieved 2026-10-17. https://docs.augmentcode.com/cli/cloud.md
37. Augment Code, "docs index", retrieved 2026-10-17. https://docs.augmentcode.com/llms.txt
38. Tembo, "Pricing – Tembo", retrieved 2026-10-17. https://www.tembo.io/pricing
39. Tembo, "Tembo", retrieved 2026-10-17. https://www.tembo.io/
40. Tembo, "Agents", retrieved 2026-10-17. https://docs.tembo.io/features/agents.md
41. Tembo, "Sandbox overview", retrieved 2026-10-17. https://docs.tembo.io/features/sandbox/overview.md
42. Tembo, "Tembo API overview", retrieved 2026-10-17. https://docs.tembo.io/api/index.md
43. Tembo, "Create a session", retrieved 2026-10-17. https://docs.tembo.io/api/v1/sessions/create-a-session.md
44. Tembo, "Tembo vs Devin", retrieved 2026-10-17. https://www.tembo.io/vs/devin
45. All Hands AI, "OpenHands Pricing", retrieved 2026-10-17. https://www.openhands.dev/pricing
46. All Hands AI, "Getting Started", retrieved 2026-10-17. https://docs.openhands.dev/openhands/usage/cloud/openhands-cloud.md
47. All Hands AI, "Cloud API Overview", retrieved 2026-10-17. https://docs.openhands.dev/openhands/usage/cloud/cloud-api.md
48. All Hands AI, "ACP Agents", retrieved 2026-10-17. https://docs.openhands.dev/openhands/usage/agent-canvas/acp-agents.md
49. All Hands AI, "GitHub Integration", retrieved 2026-10-17. https://docs.openhands.dev/openhands/usage/cloud/github-installation.md
50. All Hands AI, "Model Context Protocol (MCP) settings", retrieved 2026-10-17. https://docs.openhands.dev/openhands/usage/settings/mcp-settings.md
51. All Hands AI, "docs index (llms.txt)", retrieved 2026-10-17. https://docs.openhands.dev/llms.txt