Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Polar — A billing platform for the intelligence era

01Result

polarsource/polar ↗

polarsource/polar AI coding statistics: 22.8%

of 4,019 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
22.8% agent · top contributor 55.1%19 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

918
agent commits
3,101
other considered commits
19
agent contributors
55.1%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

891assisted
27autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0218.1%752
2026-0319%791
2026-0428.4%528
2026-0526.5%453
2026-0622.2%465
2026-0726.3%448
2026-0826%361
2026-0921.3%221

Peak month: 28.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic77819.4%
GitHub CopilotGitHub932.3%
Cursor AgentAnysphere471.2%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • 59643f3b on GitHubdocs(handbook): align on-call escalation with incident severity levels (#1Claude Code
  • 4233a69c on GitHubfix(auth): re-arm Turnstile after an expired or failed challenge (#14411)Claude Code
  • fd4886fe on GitHubRank backoffice organization search by match quality (#14352)Claude Code
  • c852c08d on GitHubfix(dashboard): use local month boundaries for customer meter activity carGitHub Copilot
  • 0ee3be36 on GitHubValidate meter ownership for product pricing (#14057)GitHub Copilot
  • 0c6e64b0 on GitHubFix AVG/UNIQUE meter totals to honor requested time range (#13919)GitHub Copilot
  • 3376142d on GitHubAlign merchant migrations UI with Polar's monochrome palette (#14521)Cursor Agent
  • 8b8ba651 on GitHubhandbook: specialized webhooks also emit the catch-all updated (ADR-0011) Cursor Agent
  • 8e4744b8 on GitHubfix(merchant-migration): allow same org to reuse a Stripe account (#14343)Cursor Agent

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window4,720
Merge commits removed−0
CI / dependency bots removed−701
Considered4,019

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Python AI coding statisticsCompare evidence across Python repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli polarsource/polar

Scan another repository

Try