← the index
garrytan/gstack
92%
of 373 commits were committed by an AI agent — a floor, not an estimate
92% agent · top contributor 96.8%6 contributors
individual

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

343
agent commits
30
human commits
6
agent contributors
96.8%
largest contributor

Assisted or autonomous

343assisted
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

Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

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

Which agents

Claude CodeAnthropic33890.6%
Cursor AgentAnysphere71.9%

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 Code
  • 702a1a9bv1.78.0.0 fix: the two-red-lanes wave — AUQ collapse rooted, OSV green froClaude Code
  • e76f65a8v1.77.0.0 feat: test-infrastructure overhaul wave 1 — matrix deletion, flaClaude Code
  • 702a1a9bv1.78.0.0 fix: the two-red-lanes wave — AUQ collapse rooted, OSV green froCursor Agent
  • 28d59ad5v1.68.0.0 fix: next tracker wave — 16 verified fixes in, 90 stale PRs and Cursor Agent
  • db149a61fix(gstack-config): accept @local endpoint ids for brain_trust_policyCursor Agent

What was excluded

Commits in window386
Merge commits removed13
CI / dependency bots removed0
Considered373

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

Scan another repository