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.

An AI-powered next-generation open source real-time observability system.

01Result

apache/hertzbeat ↗

apache/hertzbeat AI coding statistics: 8.3%

of 230 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
8.3% agent · top contributor 31.6%10 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
211
other considered commits
10
agent contributors
31.6%
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
2026-0230.8%13
2026-034.9%41
2026-040%8
2026-050%12
2026-060%9
2026-076.6%61
2026-0811.3%71
2026-096.7%15

Peak month: 30.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic125.2%
GitHub CopilotGitHub41.7%
Cursor AgentAnysphere20.9%
DevinCognition10.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 664a2533 on GitHub[doc] align Docker Compose quick-start docs with required .env and loopbacClaude Code
  • 7a8156a2 on GitHub[fix] validate sql reaching the alert query executor (#4275)Claude Code
  • 50ee6b11 on GitHub[fix] require an account to subscribe to the alert and manager streams (#4Claude Code
  • b73f824e on GitHub[Improve] Add common protoctl entity check (#4084)GitHub Copilot
  • 2bb4f434 on GitHub[improve] optimize the function of creating monitoring using AI (#3922)GitHub Copilot
  • cd406992 on GitHubrefactor: Split hertzbeat-common into core and spring modules (#4035)GitHub Copilot
  • 767ce6b0 on GitHubdocs: add H2 database security warning page (#4036)Cursor Agent
  • 09818174 on GitHub[Task] Add user account monitoring metrics for MongoDB (#4033)Cursor Agent
  • 9ec371a5 on GitHubci(doc-deploy): fix pnpm cache setup and upgrade Node to 22 (#4248)Devin

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 window230
Merge commits removed−0
CI / dependency bots removed−0
Considered230

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 →Devin commitsBrowse repositories with detected Devin 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/hertzbeat

Scan another repository

Try