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.

🤖 Dependabot's core logic for creating update PRs.

01Result

dependabot/dependabot-core ↗

dependabot/dependabot-core AI coding statistics: 16.2%

of 1,270 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
16.2% agent · top contributor 25.7%28 contributors
org-wide

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

206
agent commits
1,064
other considered commits
28
agent contributors
25.7%
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

194assisted
12autonomous

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
2026-0214%107
2026-0318.2%165
2026-0411.2%143
2026-0522.6%186
2026-0621.6%185
2026-0725.4%177
2026-084.7%254
2026-0911.3%53

Peak month: 25.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub19415.3%
Claude CodeAnthropic110.9%
OpenAI CodexOpenAI10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • e1ec1055 on GitHubSupport Bundler cooldown with Compact Index v2 publication dates (#16301)GitHub Copilot
  • 4b8a1a0f on GitHubRemove fully rolled out feature flags (#16046)GitHub Copilot
  • 1fa86740 on GitHubhelm: fix scalar image tag updates and dropped trailing newline (#16152)GitHub Copilot
  • 26c6dae0 on GitHubjulia: derive stdlib compat entries from the versions bundled across the jClaude Code
  • 3c1c54bf on GitHubSkip uv dependencies pinned to a source that can never be updated (#16132)Claude Code
  • a08a4195 on GitHubjulia: support Pkg 1.13's `registry_info` and pin the image to Julia 1.13 Claude Code
  • 5d96f6a8 on GitHubFix gradle wrapper guard (#14399)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 window2,104
Merge commits removed−595
CI / dependency bots removed−239
Considered1,270

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →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 dependabot/dependabot-core

Scan another repository

Try