← the index
dgtlmoon/changedetection.io
4.8%
of 356 commits were committed by an AI agent — a floor, not an estimate
4.8% agent · top contributor 88.2%3 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

17
agent commits
339
human commits
3
agent contributors
88.2%
largest contributor

Assisted or autonomous

17assisted
0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. The agent ran git commit during a working session, with a person there. Autonomous — a bot identity is the author, no human in the loop. Across the whole index, 93.7% of agent commits are assisted.

Agent share by month

Feb26
Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 23.5%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic174.8%

Verify it yourself

Sample commits that matched. Every one links to GitHub — check the trailers.

  • b61b83c3Fetch favicon candidates in parallel under one deadline, and stop the two Claude Code
  • 71025443xPath filters - Stop LC_COLLATE deciding what contains() means (#4437) (#4Claude Code
  • d56ec682Puppeteer fetcher - Re-navigation cap must not mean "extract right now" (#Claude Code

What was excluded

Commits in window374
Merge commits removed3
CI / dependency bots removed15
Considered356

Bots are excluded from the denominator entirely. Counting dependabot as “AI-written code” is the fastest way to produce a meaningless number.

How this was measured

Measured over February–August 2026, cloned directly. Detection is deterministic string matching against signatures agents write about themselves — no heuristics, no style analysis. Merge commits and CI bots are excluded from the denominator. The figure is a floor: squash merges strip trailers, so real usage is higher. Contributor counts are aggregate — no individual is named.

Run it yourself: npx qmmit-cli dgtlmoon/changedetection.io

Scan another repository