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 AI search platform

01Result

vespa-engine/vespa ↗

vespa-engine/vespa AI coding statistics: 5.4%

of 2,714 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

5.4% agent · top contributor 34%23 contributors

org-wide

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

147

agent commits

2,567

other considered commits

agent contributors

34%

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

131assisted

16autonomous

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: 12.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	108	4%
GitHub Copilot	GitHub	39	1.4%

03Evidence

Inspect the matches

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

Matched commit samples

878c80a8 on GitHubKeep attribute and dictionary match casing in syncClaude Code
e806dc9a on GitHubAdd regression test for swapped compressed int bounds checksClaude Code
7b967e99 on GitHubFix swapped bounds checks for compressed ints in stack dump iteratorClaude Code
bd7dadd0 on GitHubfeat(cli): add support for easier mTLS key rotation (#36942)GitHub Copilot
30d136b2 on GitHubRestore link checker app token ownerGitHub Copilot
3dc975d7 on GitHubMake link checker resilient to app token failuresGitHub Copilot

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	4,866
Merge commits removed	−1,875
CI / dependency bots removed	−277
Considered	2,714

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 →Java AI coding statisticsCompare evidence across Java 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 vespa-engine/vespa

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	3.5%	432
2026-03	3.8%	370
2026-04	2.8%	399
2026-05	2.8%	530
2026-06	10.5%	296
2026-07	5.1%	176
2026-08	9.2%	347
2026-09	12.2%	164