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 QuantLib C++ library

01Result

lballabio/QuantLib ↗

lballabio/QuantLib AI coding statistics: 2.7%

of 635 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

2.7% agent · top contributor 58.8%6 contributors

team

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

agent commits

618

other considered commits

agent contributors

58.8%

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

17assisted

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

Peak month: 9.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	10	1.6%
Claude Code	Anthropic	7	1.1%

03Evidence

Inspect the matches

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

Matched commit samples

4d482c39 on GitHubFix CPI and YoY zero-BPS tests for CICursor Agent
78b7a5b7 on GitHubAdd zero-BPS and expired fair value tests for CPI and YoY swapsCursor Agent
6cbe5bb0 on GitHubGuard zero leg BPS in CPI and YoY inflation swap fair values.Cursor Agent
a6b169eb on GitHubfix: initialize nominal in fixingDate-based MakeSwaption constructorClaude Code
80e14976 on GitHubFix duplicated words in documentation commentsClaude Code
f1229ae5 on GitHubKeep only instructions in AGENTS.md, drop the repository overviewsClaude Code

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 window	958
Merge commits removed	−265
CI / dependency bots removed	−58
Considered	635

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →C++ AI coding statisticsCompare evidence across C++ 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 lballabio/QuantLib

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	5.9%	34
2026-03	0%	80
2026-04	0%	41
2026-05	0%	71
2026-06	0%	75
2026-07	1.3%	151
2026-08	9.2%	119
2026-09	3.1%	64