f/agentlytics

Comprehensive analytics dashboard for AI coding agents — Cursor, Windsurf, Claude Code, VS Code Copilot, Zed, Antigravity, OpenCode, Command Code

What it solves

Agentlytics solves the problem of fragmented AI coding histories. When developers use multiple AI agents and editors (like Cursor, Devin, and Claude Code), their conversations, token costs, and usage patterns are siloed. This tool unifies that data into a single local dashboard for better tracking and analysis.

How it works

The tool scans local files and APIs from 17 different AI editors, normalizing the data into a local SQLite cache. It then runs a local Express server that serves this data to a React-based single-page application (SPA). For team collaboration, it includes a "Relay" feature that allows users to sync their session data to a shared server, which can then be queried by AI clients via a Model Context Protocol (MCP) server.

Who it’s for

It is designed for developers who use a variety of AI coding assistants and want to track their spending, compare the effectiveness of different editors, or share session context with teammates.

Highlights

  • Unified Dashboard: Provides KPIs, activity heatmaps, and coding streaks across all supported editors.
  • Cost Estimation: Tracks estimated AI spend broken down by model, editor, project, and month.
  • Deep Analysis: Offers tool frequency heatmaps and model distribution analytics.
  • Team Relay: Enables multi-user context sharing and exposes an MCP server for AI clients to search across team coding history.
  • 100% Local: All data is stored locally on the machine, ensuring privacy.

Related

  • Project
    kenn-io/agentsview

    A local session browser and cost tracker for AI coding agents that consolidates history and token usage across multiple tools into a single searchable interface.

  • Project
    stormzhang/token-tracker

    A local token consumption and cost tracking tool for AI agents like Claude Code, Codex, and Kimi Code, featuring real-time status bars and detailed usage reports.

  • Project
    VasiHemanth/tokentelemetry

    A local, open-source observability dashboard that tracks token usage, costs, and session traces for AI coding and autonomous agents by reading their local log files.

  • Project
    xiufengsun/TokenTracker

    A local-first token usage and cost dashboard for 31 AI coding tools, featuring a desktop pet and native widgets for real-time monitoring.

  • Project
    asheshgoplani/agent-deck

    A command center for AI coding agents that allows users to manage, monitor, and orchestrate multiple agent sessions across different projects from a single terminal.