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.

Craft beautiful websites effortlessly with an intuitive visual builder and publish them instantly

frappe/builder ↗

frappe/builder AI coding statistics: 36.4%

of 1,643 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
36.4% agent · top contributor 86%6 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

598
agent commits
1,045
other considered commits
6
agent contributors
86%
largest contributor

What shapes this result

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

Assisted or autonomous

598assisted
0autonomous

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
2026-020%28
2026-030%172
2026-043%101
2026-0511.2%196
2026-0619.1%298
2026-0764%325
2026-0859.4%453
2026-0955.7%70

Peak month: 64%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic59136%
GitHub CopilotGitHub60.4%
Cursor AgentAnysphere10.1%

Inspect the matches

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

Matched commit samples

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 window1,951
Merge commits removed−294
CI / dependency bots removed−14
Considered1,643

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

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 frappe/builder

Scan another repository