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 world's fastest open query engine for sub-second analytics both on and off the data lakehouse. With the flexibility to support nearly any scenario, StarRocks provides best-in-class performance for multi-dimensional analytics, real-time analytics, and ad-hoc queries. A Linux Foundation project.

01Result

StarRocks/starrocks ↗

StarRocks/starrocks AI coding statistics: 31.3%

of 3,195 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

31.3% agent · top contributor 19.5%61 contributors

org-wide

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

999

agent commits

2,196

other considered commits

agent contributors

19.5%

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

999assisted

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
Month	Agent share	Considered commits
2026-01	0%	1
2026-02	6.3%	288
2026-03	9.3%	432
2026-04	26.5%	437
2026-05	29.5%	448
2026-06	34.6%	546
2026-07	46.6%	489
2026-08	44.9%	365
2026-09	59.3%	189

Peak month: 59.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	940	29.4%
GitHub Copilot	GitHub	56	1.8%
Cursor Agent	Anysphere	12	0.4%
OpenAI Codex	OpenAI	2	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

7056a8d5 on GitHub[BugFix] Reject ambiguous ADD COLUMN on aggregate tables by default (#7910Claude Code
a9bbda08 on GitHub[Refactor] Give the process resident size a home in MemInfo (#79136)Claude Code
cee637ed on GitHub[BugFix] Paginate the getLoads RPC by job id (#78898)Claude Code
8ef02079 on GitHub[BugFix] Report audit statistics from connector sink operator (#74072)GitHub Copilot
8fc3acd2 on GitHub[Enhancement] Add configurable rollover file index and delete count for FEGitHub Copilot
4c9227d1 on GitHub[Enhancement] Count del-file tombstone rows toward cloud-native PK index rGitHub Copilot
b192f626 on GitHub[BugFix] Fix statistics collection for columns with dots in names (#71301)Cursor Agent
f3109c4a on GitHub[BugFix] Restrict tablet metadata dumps to the local cache (#78449)Cursor Agent
546210a3 on GitHub[BugFix] Do not swallow task exceptions in ThreadPool by default (#76863)Cursor Agent
df3d0453 on GitHub[Feature] Add asynchronous AI function execution framework with ai_completOpenAI Codex
27a2eb0e on GitHub[BugFix] Ignore recycled missing shard groups in meta sync (#76604)OpenAI Codex

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	3,197
Merge commits removed	−0
CI / dependency bots removed	−2
Considered	3,195

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 StarRocks/starrocks

Scan another repository

Try