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.

:tropical_fish: Beats - Lightweight shippers for Elasticsearch & Logstash

01Result

elastic/beats ↗

elastic/beats AI coding statistics: 14.1%

of 866 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
14.1% agent · top contributor 20.5%25 contributors
org-wide

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

122
agent commits
744
other considered commits
25
agent contributors
20.5%
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

97assisted
25autonomous

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
2026-0212.1%107
2026-0316.8%125
2026-0419.1%115
2026-0514.7%95
2026-0610.8%102
2026-078.6%152
2026-0812.6%103
2026-0922.4%67

Peak month: 22.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic657.5%
GitHub CopilotGitHub424.8%
Cursor AgentAnysphere222.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • 63ce9170 on GitHubbuild(deps): bump google.golang.org/grpc to v1.83.2 (#53124)Claude Code
  • e3e66693 on GitHubfilestream: add take_over.from_any_id for ID-agnostic state takeover (#531Claude Code
  • 10f99612 on GitHubfeat(autoops_es): collect allowlisted node attributes in node_stats (#5304Claude Code
  • 9137b724 on GitHub[Filebeat] restrict hints-based autodiscover input types (#52869)GitHub Copilot
  • 73cf66e9 on GitHubExclude Packetbeat from receiver shutdown timeout default (#52032)GitHub Copilot
  • 91aa80e9 on GitHubRestrict Buildkite Detective to open PRs (#51987)GitHub Copilot
  • 2dd729a0 on GitHublibbeat/reader/etw,x-pack/filebeat/input/etw: reconnect when the realtime Cursor Agent
  • 5ef4e309 on GitHubfix: register Kafka input Sarama metrics on the per-input registry (#53115Cursor Agent
  • b0a4ec1a on GitHubx-pack/filebeat/input/etw: Report health status to Elastic Agent (#53070)Cursor 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 window1,043
Merge commits removed−8
CI / dependency bots removed−169
Considered866

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 →Go AI coding statisticsCompare evidence across Go 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 elastic/beats

Scan another repository

Try