how-to-guide

How Multica Implements Usage Tracking and Reporting for AI Agents

April 11, 2026 multica-ai/multica ↗

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 **

Have a question about this repo?

These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:

Share the following with your agent to get started:

curl -s "https://instagit.com/install.md"

Add to your MCP client configuration:

{
  "mcpServers": {
    "instagit": {
      "command": "npx",
      "args": ["-y", "instagit@latest"]
    }
  }
}

Ask your agent:

"Use Instagit MCP to understand how multica-ai/multica works."

Works with

Claude Codex Cursor VS Code OpenClaw Any MCP Client

Maintain an open-source project? Get it listed too →