# Replicas

> The background coding agent. Delegate tasks to coding agents that work in sandboxed development environments. Backed by Y Combinator.

- Home: https://tryreplicas.com/
- Docs: https://docs.tryreplicas.com
- Pricing: https://tryreplicas.com/pricing
- Blog: https://tryreplicas.com/blog
- Resources: https://tryreplicas.com/resources
- Coding agent alternatives: https://tryreplicas.com/alternatives
- Replicas vs Devin: https://tryreplicas.com/replicas-vs-devin
- Replicas vs Cursor: https://tryreplicas.com/replicas-vs-cursor
- Replicas vs Claude Code: https://tryreplicas.com/replicas-vs-claude-code
- Cloud coding agents: https://tryreplicas.com/cloud-coding-agents
- Background coding agents: https://tryreplicas.com/background-coding-agents
- AI coding agents: https://tryreplicas.com/ai-coding-agents
- Best cloud coding agents: https://tryreplicas.com/best-cloud-coding-agents
- AI code review agent: https://tryreplicas.com/use-cases/ai-code-review-agent
- Automated code review: https://tryreplicas.com/use-cases/automated-code-review
- Code review follow-up: https://tryreplicas.com/use-cases/code-review-follow-up
- Linear issue to PR: https://tryreplicas.com/use-cases/linear-issue-to-pr
- Slack to coding agent: https://tryreplicas.com/use-cases/slack-to-coding-agent
- Backlog cleanup: https://tryreplicas.com/use-cases/backlog-cleanup
- Automated bug fixes: https://tryreplicas.com/use-cases/automated-bug-fixes
- Get started: https://tryreplicas.com/auth
- Auth notes: https://tryreplicas.com/auth.md
- Book a demo: https://cal.com/connor-replicas/30min
- Contact: founders@replicas.dev

## How it works

- **Delegate:** Assign a task from Linear, Slack, or the dashboard.
- **Sandbox:** An agent works in an isolated dev environment.
- **Pull Request:** Review the PR and merge when ready.

## Integrations

- **GitHub:** Mention @tryreplicas in any PR comment to trigger a fix.
- **Slack:** Ping @Replicas in any channel to kick off tasks.
- **Dashboard:** Chat directly from the web for full control.
- **Linear:** Assign issues directly to Replicas to start implementation.

## Sandboxed environments

Each agent runs in an isolated VM with its own dev environment: install dependencies, run databases, and verify changes locally.

## Custom workflows

Integrate Replicas in any workflow and automate code changes.

```
POST /v1/replica
{
  "repository": "acme/app",
  "message": "Add dark mode",
  "coding_agent": "claude"
}
```

## Customers

Engineering teams use Replicas to ship over 30% of pull requests, including:

- [Mintlify](https://mintlify.com)
- [Composio](https://composio.dev)
- [Fern](https://buildwithfern.com)
- [Helicone](https://helicone.ai)
- [Moda](https://modaflows.com)
- [Dart](https://dartai.com/)
- [Chronicle Labs](https://chronicle-labs.com)
- [Sorce](https://sorce.jobs)
- [Bluma](https://getbluma.com)
- [Knowunity](https://knowunity.com)
- [Trellis](https://runtrellis.com)
- [Hyperspell](https://www.hyperspell.com)
- [Totalis](https://totalis.trade)

## FAQ

### What coding agents are supported?
Claude Code, Codex, Cursor, and Opencode.

### How is my code kept secure?
Each workspace runs in an isolated VM. Your code never leaves your connected repository, and we don’t train on your data.

### Do you store my code?
No. Only you have SSH access to your workspaces, and no code is stored in our databases. Sleeping workspaces are automatically deleted after 7 days of inactivity.

### What repositories can I use?
Any GitHub repository you have access to. Connect your GitHub account and select which repos to enable.

### How does billing work?
Usage is measured in minutes of workspace runtime. Every plan includes a monthly allowance of minutes, and you pay only for active compute time. Workspaces automatically sleep when idle and wake on demand.
