One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
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: 100%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 338 | 90.6% |
| Cursor Agent | Anysphere | 7 | 1.9% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
0d1bd561v1.79.0.0 fix: ship subagent dispatches can no longer strand the run (#497Claude Code702a1a9bv1.78.0.0 fix: the two-red-lanes wave — AUQ collapse rooted, OSV green froClaude Codee76f65a8v1.77.0.0 feat: test-infrastructure overhaul wave 1 — matrix deletion, flaClaude Code702a1a9bv1.78.0.0 fix: the two-red-lanes wave — AUQ collapse rooted, OSV green froCursor Agent28d59ad5v1.68.0.0 fix: next tracker wave — 16 verified fixes in, 90 stale PRs and Cursor Agentdb149a61fix(gstack-config): accept @local endpoint ids for brain_trust_policyCursor Agent
What was excluded
| Commits in window | 386 |
| Merge commits removed | −13 |
| CI / dependency bots removed | −0 |
| Considered | 373 |
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 garrytan/gstack