← the index
ceph/ceph ↗
0.2%
of 4,487 commits were committed by an AI agent — a floor, not an estimate
0.2% agent · top contributor 18.2%8 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

11
agent commits
4,476
human commits
8
agent contributors
18.2%
largest contributor

Assisted or autonomous

10assisted
1autonomous

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: 0.5%. Bars are scaled to that peak, not to 100%.

Which agents

Cursor AgentAnysphere60.1%
Claude CodeAnthropic30.1%
GitHub CopilotGitHub20%

Verify it yourself

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

  • 4af86741crimson: fix stack-use-after-return in ConfigProxy::parse_argvCursor Agent
  • 330c4137cephadm: warn when orch actions are deferred on unmanaged servicesCursor Agent
  • 4fe341c7qa/suites/orch/cephadm/smb: retry CTDB deleted-node check via workunitCursor Agent
  • 7b7aceb1rgw: add GCM hardware acceleration support via CryptoAccelClaude Code
  • dfdbb84argw: add AES-256-GCM (AEAD) support for server-side encryptionClaude Code
  • 0d8a70b6test/rgw/notifications: migrate from nose to pytestClaude Code
  • 6d8851a2rgw: add tcmalloc heap profiler support via admin socketGitHub Copilot
  • ebb5d25dcopilot: add GitHub Copilot instructionsGitHub Copilot

What was excluded

Commits in window6,704
Merge commits removed−2,217
CI / dependency bots removed−0
Considered4,487

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 ceph/ceph

Scan another repository