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.

SeaTunnel is a multimodal, high-performance, distributed, massive data integration tool.

01Result

apache/seatunnel ↗

apache/seatunnel AI coding statistics: 6.4%

of 957 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
6.4% agent · top contributor 26.2%23 contributors
org-wide

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

61
agent commits
896
other considered commits
23
agent contributors
26.2%
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

61assisted
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%28
2026-031.9%54
2026-041.8%57
2026-052.3%87
2026-064%125
2026-075.2%231
2026-088.6%198
2026-0913%177

Peak month: 13%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic424.4%
Cursor AgentAnysphere171.8%
GitHub CopilotGitHub40.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 60446da9 on GitHub[Fix][E2E] Unify testcontainers version to 1.21.4 across all e2e connectorClaude Code
  • ae9132fe on GitHub[Fix][Zeta] Checkpoint restore remap duplicates subtask state for parallelClaude Code
  • bd09f6d9 on GitHub[Feature][Connector-V2] Support ADD COLUMN schema evolution for BigQuery (Claude Code
  • f6d230ec on GitHub[Feature][Format] Add Debezium JSON SerDe microbenchmarks (#12056)Cursor Agent
  • 99e53aad on GitHub[Feature][Connector-V2] Add BosFile source and sink connector (#11952)Cursor Agent
  • 7c73866c on GitHub[Feature][Zeta] Add selectable live metrics chart on Job Detail (#11957)Cursor Agent
  • 30f4c985 on GitHub[Fix][E2E] Stabilize engine failover test and rebalance connector shards (GitHub Copilot
  • 6fc6ac7f on GitHub[Docs] add FAQ sections to connector pages (EN + zh-CN) (#10980)GitHub Copilot
  • 5b708afd on GitHub[Fix][Engine] Fix JDK 8 NoSuchMethodError in StainTracePayload#append (#10GitHub 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 window957
Merge commits removed−0
CI / dependency bots removed−0
Considered957

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 →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 apache/seatunnel

Scan another repository

Try