Cursor's usage dashboard shows your included usage per pool, and Teams admins get a team analytics dashboard and an Admin API. Zest puts each engineer's Cursor sessions, models and skills next to their other coding agents and merged pull requests.
Claude CodeFable 5.1 (max) (with fallback)70.4 · Coding Agent Index
CodexGPT-6 Astra (max)67.0 · Coding Agent Index
Muse CodeMuse Spark 1.3 (xhigh)64.2 · Coding Agent Index
Grok BuildGrok 4.5 (high)64.1 · Coding Agent Index
Kimi Code CLIKimi K362.6 · Coding Agent Index
OpencodeGemini 3.8 Flash (high)61.2 · Coding Agent Index
Cursor CLIComposer 2.5 Fast38.3 · Coding Agent Index
Demo setups use current model families. The pairings above are the combinations benchmarked by Artificial Analysis; rankings measure performance, not popularity.
Illustrative daily trends · Other totals: last 30 days. Build Hours: this week, model-estimated activity including overlap; not engineer hours.
↓ Scroll to explore
USED BY ENGINEERING TEAMS AT
How to check Cursor usage
Cursor shows usage stats in two places, both about Cursor alone. Neither puts Cursor next to the other coding agents each engineer runs, or next to what merged:
A usage dashboard and editor settings show included usage per pool, Cursor models and other models.
Teams dashboard: AI share of committed code, agent edits, messages by model, daily users and a leaderboard.
Cursor usage tracking with Zest
Each engineer installs the Zest extension in Cursor with one click. It reads Cursor's local chat history (composer conversations and agent transcripts) and syncs each session with its models and timings. Optionally, it adds each session's token usage and cost from Cursor's usage dashboard.
Cursor is the agent our own team runs least: it co-authored 7 of the 3,192 commits in our two repos from July 5 to October 3, 2026. What this page says about Cursor comes from Cursor's docs and the extension's code, not from our usage.
Skills and MCP tools in each Cursor session, rolled up per engineer in the AI Stack view.
Redaction runs on the engineer's machine before upload; no code diffs are sent.
Cursor Admin API and Analytics API
Cursor's own APIs are the do-it-yourself route. The Admin API returns your team's members, daily usage data and spend. The Analytics API returns adoption metrics: agent edits, tab usage, daily active users, model usage, MCP and skills adoption. Both need an admin API key, and both describe Cursor alone.
What that spend buys, plan by plan, is on Cursor pricing.
Cursor usage next to what ships
Connect the Zest GitHub App and each engineer's Cursor sessions sit next to the pull requests they opened and merged.
TRY IT ON YOUR TEAM
See what your team ships with AI.
Starter is free (3 seats, no credit card). Pro is $49 a month with 5 seats and Max is $149 a month with 10 seats — priced per workspace, not per engineer, with extra seats at $19 a month.
Each engineer installs the Zest extension in Cursor, and an admin connects your GitHub org. Zest then shows Cursor sessions per engineer (models, skills and, optionally, tokens and cost) next to the pull requests they opened and merged.
Can I compare Cursor with Claude Code and Codex?+
Yes. Zest reports Claude Code, Codex, GitHub Copilot Chat, Grok Build and Hermes sessions on the same dashboard, so you can see which tool and model each engineer reaches for.
Is there a free plan?+
Yes. Starter is $0 per workspace per month with 3 seats included and no credit card. It includes Coding agent analytics, Models & Skills analytics, AI cheatcodes.