#22 · Primary category: AI Usage & Cost Monitoring
agentlytics
Comprehensive analytics dashboard for AI coding agents — Cursor, Windsurf, Claude Code, VS Code Copilot, Zed, Antigravity, OpenCode, Command Code
Project last updated:08/03/26
GitHub Stars
567
Forks
83
Contributors
17
License
Other
Why we included this project
Working across more than one AI coding tool usually means your session history is split between several siloed apps. Agentlytics reads the local session stores of Cursor, Claude Code, VS Code Copilot, Zed, and a dozen other editors, normalizes them into a single SQLite cache, and serves a React dashboard on localhost. From there you can check cost estimates per model, editor, or project, break down token and tool usage, search across all your conversations, and compare editors side by side. Everything runs locally and nothing leaves your machine, which matters for teams that want usage visibility without shipping telemetry to a third party. An optional relay mode lets a small team share session context over a trusted local network through an MCP endpoint.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
CodexBar
Show usage stats for OpenAI Codex and Claude Code, without having to login.
codeburn
Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn
Claude-Code-Usage-Monitor
Real-time Claude Code usage monitor with predictions and warnings
helicone
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
agentsview
Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents.