Welcome to Plexus
Welcome to the Plexus documentation. Learn how to monitor all your AI agents in one place.
Plexus is a local-first observability platform for AI coding agents. It provides a unified dashboard to monitor and understand what all your AI agents are doing across multiple terminals and sessions.
Note: This project is in early development (v0.1.0).
Why Plexus?
Modern developers often run multiple AI agents simultaneously - Claude Code in one terminal, Cursor in another, and Gemini CLI for quick lookups. Managing this chaos is difficult:
- Which agent needs my attention? Hard to tell when juggling multiple sessions across terminals.
- How much am I spending? API costs pile up without visibility.
- What happened yesterday? Finding past conversations requires digging through logs.
Plexus solves these problems with a unified dashboard that shows all your agents at a glance.
Key Features
- Real-time Monitoring - Track multiple AI agent sessions simultaneously
- Agent Hooks - Native integration for Claude Code, Cursor, and Gemini CLI
- Focus Terminal - Quickly jump to agent terminals requiring attention
- Session History - SQLite-based history with cost tracking
- Notifications - Discord/Slack webhooks when agents need attention
- Local-First - All data stays on your machine, no cloud required
Supported Platforms
| Platform | Status |
|---|---|
| macOS (Apple Silicon) | Fully Supported |
| macOS (Intel) | Fully Supported |
| Windows | Fully Supported |
| Linux | Fully Supported |
Getting Started
Ready to take control of your AI agents?