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.

Apache Fluss is a streaming storage built for real-time analytics.

01Result

apache/fluss ↗

apache/fluss AI coding statistics: 2.1%

of 912 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.1% agent · top contributor 21.1%14 contributors
org-wide

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

19
agent commits
893
other considered commits
14
agent contributors
21.1%
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

19assisted
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%179
2026-030%106
2026-041.6%126
2026-050.9%109
2026-068.2%85
2026-072.8%108
2026-082.4%127
2026-094.2%72

Peak month: 8.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic131.4%
OpenAI CodexOpenAI40.4%
GitHub CopilotGitHub10.1%
Cursor AgentAnysphere10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • dfd77826 on GitHub[docs] Document Spark scan.maxRecordsPerPartition (#4049)Claude Code
  • a66a6e4a on GitHub[flink] Integrate FIP-17 server-side KV scan into Flink connectorClaude Code
  • c77ca8be on GitHub[website] Add consent-gated kapa.ai "Ask AI" widget to docs site (#3760)Claude Code
  • ee584f89 on GitHub[server] Add per-tablet-server sender retry framework (#3391)OpenAI Codex
  • 9ae3ab55 on GitHub[client] Clean up batches when synchronous sends fail (#4028)OpenAI Codex
  • 3a000ba6 on GitHub[test] Wait for KV flush before limit scanOpenAI Codex
  • 5cacbb02 on GitHub[client] Add log read preference for remote-first fetch (#3606)GitHub Copilot
  • 61a6593b on GitHub[python] Split examples in Python and enforce executability in CI for pythCursor Agent

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 window925
Merge commits removed−1
CI / dependency bots removed−12
Considered912

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 apache/fluss

Scan another repository

Try