• pgEdge AI DBA Workbench
• Using Binary Files to Install Workbench
• Building Workbench from Source
• Installing and Configuring pgEdge AI DBA Workbench:
  • Installation Overview
  • Quick Start - Installing with Binaries
  • Building from Source Code
  • Deploying with Docker
  • Configuration Details:
    • Server
    • Collector
    • Alerter
    • Web Client
    • Configuring systemd Services
• User Guide:
  • Using the Workbench
  • Monitoring Dashboards:
    • Dashboard Overview
    • Estate Dashboard
    • Cluster Dashboard
    • Server Dashboard
    • Database Dashboard
    • Object Dashboard
  • Alerts:
    • Understanding Alerts
    • Alert Reference
    • AI Alert Analysis
  • Blackout Management
  • AI Features:
    • AI Overview
    • Ask Ellie
    • Connecting MCP Clients
  • MCP Tools
• Administrator's Guide:
  • Overview
  • Verifying the Health of Components
  • Users & Authentication
  • Connection Management
  • Alert Rules & Thresholds
  • Notification Channels
  • Probe Configuration
  • REST API:
    • API Reference
    • API Browser
    • Server Information
    • Metrics API
• Developer's Guide:
  • Overview
  • Contributing
  • Collector:
    • Architecture
    • Schema Design
    • Schema Management
    • Scheduler
    • Probes
    • Adding Probes
    • Probe Reference
    • pg_settings Usage
    • Testing
  • Alerter:
    • Architecture
    • Anomaly Detection
    • Adding Rules
    • Cron Expressions
    • Testing
  • Server:
    • Architecture
  • Client:
    • Architecture
  • Design:
    • Node Role Probe
• Changelog
• Issues
• Contributing
• License

The pgEdge AI DBA Workbench is a unified environment for monitoring and management of any PostgreSQL v14+ instance, including Supabase and Amazon RDS, with an optional AI agent. The Workbench watches every instance, catches anomalies before they become outages, and walks through diagnosis and resolution step by step.

The Workbench combines a Model Context Protocol (MCP) Server with a web-based user interface and data collector. Users can query, analyze, and manage distributed clusters using natural language and intelligent automation. The Workbench exposes pgEdge tools and data sources such as Spock replication status, cluster configuration, and operational metrics to language models.

The architecture supports switching between cloud-connected LLMs like Claude and locally hosted models from Ollama. This design ensures similar levels of functionality in air-gapped or secure environments. The pgEdge AI DBA Workbench bridges database administration and AI reasoning; it offers an extensible foundation for observability, troubleshooting, and intelligent workflow creation across the pgEdge ecosystem.

The pgEdge AI DBA Workbench consists of four main components:

• The Collector monitors PostgreSQL servers and stores metrics in a centralized datastore.
• The Server provides MCP tools and resources for interacting with PostgreSQL systems.
• The Alerter evaluates collected metrics against thresholds and AI-powered anomaly detection to generate alerts.
• The Client provides a web-based user interface for the AI DBA Workbench.

The Workbench can be:

• installed with binary files from the Github repo.
• built from source code from the Github repo.
• deployed in a Docker container.
• installed with packages from the pgEdge repository.

Pre-built binary files for Workbench are available from the pgEdge repo at: https://github.com/pgEdge/ai-dba-workbench/releases.

The Quick Start - Installing with Binaries guide contains detailed instructions for using the binary files to install and configure the Workbench.

The Workbench can be built from source for local development or to produce custom binaries.

The Quick Start - Building from Source guide contains detailed instructions for cloning the repository, satisfying build dependencies, and compiling the Workbench: Building from Source.

Pre-built container images for Workbench are published to the GitHub Container Registry for each release.

The Quick Start - Docker Deployment guide contains detailed instructions for deploying the Workbench using Docker Compose: Docker Deployment.

To report an issue with the software, visit: GitHub Issues

We welcome your project contributions; for more information, see docs/developer-guide/contributing.md.

For more information, visit docs.pgedge.com.

This project is licensed under the PostgreSQL License.