> ## Documentation Index
> Fetch the complete documentation index at: https://www.qovery.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Autonomous Agents

> AI agents that autonomously resolve issues from your project tracker and open pull requests.

<Warning>
  **Preview**: AI Builder Portal is in preview. Features and capabilities are under active development and may change.
</Warning>

Autonomous agents pick up issues from your project tracker, work on them in isolated cloud environments, and open pull requests - without human intervention. They use the same blueprint and governance infrastructure as workspaces, but operate autonomously.

Linear and Jira are supported as project trackers. A GitHub Issues integration is planned.

## How It Works

When a user triggers the agent on an issue - by @mentioning or assigning it in Linear, or by assigning it to the agent's user in Jira - the agent claims it, launches a workspace, writes the code, opens a pull request, and shuts down. Progress is reported back on the issue in real time.

```mermaid theme={null}
flowchart LR
    A["Agent triggered\non issue"] --> B["Agent\nclaims issue"]
    B --> C["Workspace\nlaunches"]
    C --> D["Agent\nwrites code"]
    D --> E["PR opened"]
    E --> F["Workspace\nstopped"]

    style A fill:#642DFF,color:#fff
    style B fill:#7C3FFF,color:#fff
    style C fill:#965FFF,color:#fff
    style D fill:#965FFF,color:#fff
    style E fill:#7C3FFF,color:#fff
    style F fill:#642DFF,color:#fff
```

## Agents vs Workspaces

Autonomous agents and workspaces share the same underlying infrastructure but serve different workflows.

|                    | Workspaces             | Autonomous Agents                           |
| ------------------ | ---------------------- | ------------------------------------------- |
| **Trigger**        | Human clicks "Create"  | Agent triggered from a Linear or Jira issue |
| **Interaction**    | Human works in browser | AI agent runs autonomously                  |
| **Output**         | Running application    | Pull request                                |
| **Lifecycle**      | Manual start/stop      | Auto-launch, auto-stop on completion        |
| **Blueprint type** | Workspace Blueprint    | Agent Blueprint                             |
| **Admin view**     | Workspace Management   | Agents Dashboard & Runs                     |

## Supported Runtimes

Each agent blueprint specifies which AI coding runtime to use. The runtime determines the CLI tool that drives the agent inside the workspace.

<CardGroup cols={3}>
  <Card title="Claude Code" icon="terminal">
    Anthropic's coding agent. Runs `claude -p` with the issue description as the prompt.
  </Card>

  <Card title="OpenCode" icon="code">
    Open-source coding agent. Runs `opencode run` to process the issue autonomously.
  </Card>

  <Card title="Codex" icon="microchip">
    OpenAI's coding agent. Runs `codex --full-auto` for fully autonomous operation.
  </Card>

  <Card title="Gemini CLI" icon="gem">
    Google's coding agent. Runs `gemini -p` with the issue context as input.
  </Card>

  <Card title="Cursor CLI" icon="arrow-pointer">
    Cursor's agent mode. Runs `cursor-agent` to resolve the issue.
  </Card>
</CardGroup>

## Shared Infrastructure

Autonomous agents run on the same Kubernetes cluster as workspaces. They use the same split architecture - the portal orchestrates agent runs from `rde.qovery.com`, while the agent containers execute on your infrastructure. The same security model applies: no inbound ports, outbound-only TLS/gRPC tunnels, and all code stays on your cluster.

For details on the underlying infrastructure, see [Architecture](/docs/rde/reference/architecture) and [Security & Data Residency](/docs/rde/reference/security).

## Supported Project Trackers

Both trackers connect via OAuth and auto-refresh their tokens. You configure which tracker an agent blueprint uses in the [Create Agent Blueprint](/docs/rde/agents/getting-started#create-an-agent-blueprint) wizard.

* **Linear** - trigger agents by @mentioning or assigning them on issues. The agent responds with a real-time plan and progress updates visible directly in Linear as agent activities. See [Linear Integration](/docs/rde/agents/linear-integration).
* **Jira** - trigger agents by assigning an issue to the agent's Jira user. Progress is reported as issue comments and workflow status transitions. See [Jira Integration](/docs/rde/agents/jira-integration).

<Info>
  A **GitHub Issues** integration is planned. If you need a specific integration, contact the Qovery team.
</Info>

## Next Steps

<CardGroup cols={2}>
  <Card title="Getting Started" icon="play" href="/docs/rde/agents/getting-started">
    Set up your first autonomous agent with Linear integration.
  </Card>

  <Card title="Agent Blueprints" icon="cubes" href="/docs/rde/agents/agent-blueprints">
    Configure blueprints that define how agents run.
  </Card>

  <Card title="Managing Runs" icon="list-check" href="/docs/rde/agents/managing-runs">
    Monitor agent runs, review results, and troubleshoot failures.
  </Card>

  <Card title="Linear Integration" icon="link" href="/docs/rde/agents/linear-integration">
    Connect Linear, configure labels, and manage issue routing.
  </Card>

  <Card title="Jira Integration" icon="link" href="/docs/rde/agents/jira-integration">
    Connect Jira, map statuses, and trigger agents by assignment.
  </Card>
</CardGroup>