# Everruns Cloud

**Navigation:** [Products](/products/) | [Platform](/products/platform) | [Blog](/blog/) | [Docs](https://everruns.com/docs/) | [GitHub](https://github.com/everruns/everruns)

---

> Everruns, fully managed (Early access)

Everruns Cloud is the hosted edition of the open-source platform. We run the server, database, and workers, so you can build and ship durable AI agents without operating any infrastructure. It is open to everyone in early access, with built-in model access or your own provider keys.

Open Everruns Cloud: https://app.everruns.com

Built-in model access with $5 of starter credit, prepaid top-ups, or bring your own keys.

---

The web console you get on sign-up. Cloud runs the same console that ships with the open-source core.

---

## Getting started

1. Create an account at app.everruns.com, with an email and password or your Google account.
2. Pick a model. Use the built-in Everruns provider, which starts with $5 of credit on your first organization, or connect your own API key from OpenAI, Anthropic, Google, AWS Bedrock, and more.
3. Create an agent, give it capabilities and integrations, and run it. Progress is durable, so a restart resumes instead of starting over.
4. Or let your coding agent do it: install the Everruns plugin from github.com/everruns/plugins in Claude Code, Codex, Cursor, or Gemini CLI, then ask it to build, run, debug, or ship an agent.

---

## What you get

The same platform you can run today, operated for you and ready for teams.

### Managed and hosted

We run the Everruns server, PostgreSQL, and background workers. No clusters to provision, patch, or scale, just create agents and run them.

### Built for teams

One Everruns account signs you in across Everruns cloud surfaces, then organizations, members, and invitations keep work separated by team.

### The same open-source core

Cloud runs the same open-source Everruns platform. No lock-in, self-host the identical stack whenever you want.

### Durable by default

Long-running agents keep the durable execution guarantees Everruns is built on: persisted progress and recovery from crashes, restarts, and worker loss.

---

## Open source, with a managed option

Everruns is open source and MIT-licensed, you can self-host the full platform right now from github.com/everruns/everruns. Everruns Cloud is the managed option built on top of it, and it is in early access: expect rough edges, and tell us what breaks.

---

## Product updates

Occasional email about what ships in Everruns Cloud. No spam, unsubscribe anytime.

To subscribe: open https://everruns.com/cloud/ and enter your email in the product updates form. You can unsubscribe anytime from any email we send.

[Back to home](/)

---

## Machine-readable entry points

- [/llms.txt](https://everruns.com/llms.txt): index of this site written for language models.
- [/llms-full.txt](https://everruns.com/llms-full.txt): every page on this site as one document.
- [/auth.md](https://everruns.com/auth.md): how an agent obtains Everruns API credentials.
- [/.well-known/ai-catalog.json](https://everruns.com/.well-known/ai-catalog.json): ARD capability manifest.
- [/.well-known/mcp/server-card.json](https://everruns.com/.well-known/mcp/server-card.json): MCP server card for Everruns Cloud.
- [/.well-known/agent-skills/index.json](https://everruns.com/.well-known/agent-skills/index.json): agent skills for working with Everruns.

Any page on this site serves Markdown to `Accept: text/markdown`.