Cursor usage
Tab completions, agent runs, tokens, and spend from the Cursor Analytics API.
Product
Track usage metrics across multiple LLMs and coding assistants — Cursor, Copilot, OpenAI, and Claude — with AI tool usage tracking your VP Eng can share with finance.
Missing a tool or feature?
One dashboard for IDE assistants and API keys. No proxy, no browser plugin: official vendor APIs only.
Tab completions, agent runs, tokens, and spend from the Cursor Analytics API.
Acceptance rate, active users, and seat utilization from Copilot Metrics.
OpenAI and Anthropic org usage in one view: model mix, tokens, and cost.
Sync now or every day at 06:00 UTC, with email reports when a pull completes.
Most teams start with spend and DAU. Then they need cost per developer, idle Copilot seats, model mix, and which repos burn agent tokens. Those are the custom AI metrics ForgeMeter builds from synced usage, not a one-off export.
When you need the number for a board deck, generate an executive audit or keep a live workspace on daily sync.
A local script can show one developer's tokens. Engineering leaders need AI tool usage tracking for the org: who spent what, on which assistant, this month. ForgeMeter reads the Cursor, GitHub Copilot, OpenAI, and Anthropic admin APIs and lists token consumption by team and by AI tool in one dashboard.
That is the same view people look for when they ask whether Jellyfish, a spreadsheet, or three vendor consoles can combine Copilot, Cursor, and Claude Code. Connect the official APIs, sync daily, and the AI usage tracker stays current without a proxy on the developer machine. For the category around spend and ROI, see AI engineering analytics.
Engineering tool usage, not production traces.
An AI usage tracker records how developers use coding assistants and LLM APIs (seats, tokens, models, and cost) so leaders can see adoption and spend in one place. ForgeMeter tracks Cursor, GitHub Copilot, OpenAI, and Anthropic via official APIs.
Connect each provider's usage or admin API, normalize tokens and dollars into one schema, then review per-developer and per-model breakdowns. ForgeMeter does that on a daily sync so you are not exporting CSVs from four consoles.
Yes. Start with spend, tokens, DAU, and Copilot acceptance rate, then slice by team, repo, and model. Custom AI metrics in ForgeMeter are built from the same synced usage, not a separate spreadsheet.
ForgeMeter syncs Cursor, GitHub Copilot, OpenAI, and Anthropic admin APIs into one workspace, then breaks tokens and dollars down by developer and by tool. A local CLI only sees the machine it runs on.
Yes. Connect each vendor's official usage API. ForgeMeter normalizes seats, tokens, and cost so an engineering leader sees Copilot, Cursor, and Claude together instead of three admin consoles.
No. Those tools observe traces in production applications. An engineering AI usage tracker measures IDE assistants and team API keys, the tools developers use to write software.
Free workspace with usage sync. Connect one integration and see live metrics in minutes.
Missing a tool or feature?