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.

Modern, Streamlined, Free and Open Source Customer Service Software

frappe/helpdesk ↗

frappe/helpdesk AI coding statistics: 8.4%

of 1,977 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
8.4% agent · top contributor 67.5%2 contributors
individual

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

166
agent commits
1,811
other considered commits
2
agent contributors
67.5%
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

166assisted
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%235
2026-030%168
2026-040%343
2026-050%368
2026-066.7%326
2026-0722.9%271
2026-089.6%156
2026-0960.9%110

Peak month: 60.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1668.4%

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 window2,297
Merge commits removed−320
CI / dependency bots removed−0
Considered1,977

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/helpdesk

Scan another repository