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.

The BBC's Open Source Web Application. Contributions welcome! Used on some of our biggest websites, e.g.

bbc/simorgh ↗

bbc/simorgh AI coding statistics: 4.2%

of 3,029 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
4.2% agent · top contributor 27.6%18 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

127
agent commits
2,902
other considered commits
18
agent contributors
27.6%
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

127assisted
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
2026-021.2%433
2026-031.4%346
2026-041.9%315
2026-0511.7%513
2026-064.2%527
2026-072.9%480
2026-083.6%250
2026-093.6%165

Peak month: 11.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub1274.2%

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 window5,057
Merge commits removed−1,915
CI / dependency bots removed−113
Considered3,029

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 bbc/simorgh

Scan another repository