# How Multica Implements Usage Tracking and Reporting for AI Agents

> Discover how Multica implements AI agent usage tracking and reporting. Learn about token consumption, event capture, and PostgreSQL integration for REST API insights.

- Repository: [multica-ai/multica](https://github.com/multica-ai/multica)
- Tags: how-to-guide
- Published: 2026-04-11

---

**Multica tracks LLM token consumption at the agent task and runtime level by capturing usage events in agent implementations, transmitting them via the local daemon to PostgreSQL through UPSERT operations, and exposing aggregated REST endpoints for workspace and runtime reporting.**

Multica is an open-source platform for orchestrating AI coding agents. Its usage tracking and reporting system provides granular visibility into token consumption across agent tasks and persistent runtimes, enabling teams to monitor costs and optimize resource allocation according to the multica-ai/multica source code.

## Token Collection Inside Agent Implementations

Each agent implementation maintains a **