A small group is using agents. Adoption has spread beyond one person but is not project-wide.
Assisted or autonomous
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
Peak month: 69.6%. Bars are scaled to that peak, not to 100%.
Which agents
| GitHub Copilot | GitHub | 74 | 22.4% |
| Claude Code | Anthropic | 6 | 1.8% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
342a0b0aFix concurrent workflow review feedbackGitHub Copilot39f1ae56fix: mirror concurrent aggregation fix in lesson 08 notebookGitHub Copilotc106b1ccUse StringBuilder for streamed message aggregationGitHub Copilotde8a3476Align envelope with the lesson's receipt shape; fold follow-on into LessonClaude Code7c3e7367Shared envelope + verify_chain per review: stale-authority and digest-subsClaude Code09ce7e26Fix fail-closed gaps: wrong-length signature and non-dict payload now refuClaude Code
What was excluded
| Commits in window | 1,005 |
| Merge commits removed | −284 |
| CI / dependency bots removed | −390 |
| Considered | 331 |
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 microsoft/ai-agents-for-beginners