Quickstart

Get developerz.ai running on your repo in under five minutes. This guide covers the full path: issue triage → AI dev dispatch → CI → merged PR. You can stop at any step — every feature is independently useful.

1. Install the GitHub App

Go to github.com/apps/developerz-ai and click Install. Grant access to the repositories you want to manage.

2. Add a .maintainer.yml

Create .maintainer.yml at your repository root:

# yaml-language-server: $schema=https://developerz.ai/schemas/maintainer.v1.json
version: 1

Every field is optional. An empty file with only version: 1 enables safe defaults: friendly triage, no handoff, weekly digest. See the .maintainer.yml reference for all fields.

Editor autocomplete. The yaml-language-server comment wires the JSON Schema so you get validation and hover docs in VS Code, Cursor, and JetBrains.

3. Add your model key

developerz.ai is BYOK — bring your own key. We never proxy or resell tokens.

In the dashboard, go to Settings → Model keys and add your inference key:

Your key is encrypted at rest and never logged. See the security doc.

4. Watch the first loop

Open a new issue in your repo. Within seconds the bot will:

1. Read the issue and check for duplicates.
2. Ask for reproduction steps if required fields are missing (configurable).
3. Qualify the issue: bug, feature, question, or dupe.
4. Hand off to your coding agent if handoff.mode is set.

Every comment begins with the bot disclosure footer and is written to the audit log.

5. Enroll a box (AI devs + CI runners)

To run AI coding tasks or self-hosted CI, enroll a VPS or cloud VM:

# On your VPS — download the installer, verify its published checksum, then run it
curl -fsSLO https://developerz.ai/install.sh
curl -fsSL  https://developerz.ai/install.sh.sha256 | sha256sum -c -
bash install.sh

# Follow the prompt for your enrollment token (from Settings → Fleet → Add box)

Opt-in quick path. curl -fsSL https://developerz.ai/install.sh | bash runs the installer in one line with no version pin or checksum. Only use it on throwaway boxes where you accept running unverified remote code — prefer the verified download above everywhere else.

The installer sets up the runner as a systemd service. Once enrolled, the box appears in Fleet → Boxes in the dashboard and is ready for tasks.

Supported OS

Ubuntu 22.04+ (x86-64 or ARM64). 2 GB RAM minimum; 8 GB+ recommended for parallel workloads.

6. Dispatch your first task

From Claude Code

Add the developerz.ai MCP server to your Claude Code config:

// .claude/settings.json
{
  "mcpServers": {
    "developerz": {
      "command": "mcp-remote",
      "args": ["https://mcp.developerz.ai"],
      "env": { "MCP_BEARER_TOKEN": "dzai_live_…" }
    }
  }
}

Create a PAT at Settings → API tokens with write:tasks scope, then:

Hey Claude, use task_create to dispatch "add pagination to the user listing endpoint"
to owner/my-repo as a gh task.

The bot scouts the repo, dispatches the task to your coding agent, and watches the resulting PR and CI before requesting merge.

From Claude Desktop

Same MCP config. Add developerz to your claude_desktop_config.json:

{
  "mcpServers": {
    "developerz": {
      "command": "mcp-remote",
      "args": ["https://mcp.developerz.ai"],
      "env": { "MCP_BEARER_TOKEN": "dzai_live_…" }
    }
  }
}

Then ask Claude Desktop to dispatch a task the same way.

From a phone (mobile MCP client)

Any MCP-capable iOS or Android client that supports bearer-token auth works. The endpoint is https://mcp.developerz.ai; your PAT goes in the bearer header. Use task_create to dispatch, box fleet_status to check progress, and task list to see the queue — without a laptop in sight.

7. Enable CI runners

Change one line in any GitHub Actions workflow:

jobs:
  test:
    runs-on: developerz-2vcpu  # was: ubuntu-latest

Push the change. The next workflow run routes to your enrolled box. Logs are stored for 72 hours and downloadable from the dashboard or via the ci log_url MCP verb.

See the CI runners doc for the full security model and label reference.

8. Enable AI code review

Add a review: block to .maintainer.yml (or keep your existing .coderabbit.yaml — the reviewer reads both, with the native block taking precedence):

review:
  profile: chill
  anti_noise:
    severity_floor: minor
    max_comments: 30

The reviewer triggers on every push to a PR. See the AI review doc.

What happens next

Every action is written to the append-only audit log. Nothing happens silently.