Docs / Overview
Documentation
Install the GitHub App, write your .maintainer.yml policy, and learn how the maintainer agent triages, hands off, and ships — every action audited.
# yaml-language-server: $schema=https://developerz.ai/schemas/maintainer.v1.json
version: 1- Quickstart
Install the GitHub App, drop a .maintainer.yml, and watch the first loop run.
- .maintainer.yml reference
Every policy field, with examples — the file that bounds what the agent may do.
- MCP verb reference
All MCP tools — user-tier and operator-tier — with scopes and actions.
- AI code review
CodeRabbit-compatible AI review on your own model. Drop in your .coderabbit.yaml or use the native review: block.
- Self-hosted CI
Replace GitHub-hosted runners with your own VPS. One label change — runs-on: [self-hosted, linux, developerz].
- Artifact storage
Agents store files in your S3 bucket or the platform bucket. Presigned URLs, expiry by policy.
- BYO log sink & retention
Raw CI/review/run logs are kept 72 hours. Point a Postgres you own at the platform for retention on your terms.
- Realtime dashboards
JSON-defined boards pushed live over SSE. Define from Claude Code or Claude Desktop.
- REST API
Programmatic access to your repos, tasks, runners, billing, and audit log.
- Escalations
When the agent pages a human: security, breaking changes, and stuck threads.
- BYOK
Bring your own model key. We orchestrate; you own the inference bill.
- Security
Least-privilege GitHub scopes, encrypted secrets, and the append-only audit log.