61.6%

of 1,866 commits were committed by an AI agent — a floor, not an estimate

61.6% agent · top contributor 90.6%17 contributors

individual

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

1,150

agent commits

716

human commits

agent contributors

90.6%

largest contributor

Assisted or autonomous

1150assisted

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: 93.3%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code	Anthropic	1147	61.5%
Gemini CLI	Google	4	0.2%
Cursor Agent	Anysphere	1	0.1%

Verify it yourself

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

d5b38fa7fix(ci): distinguish copied inventory from download payloads (#2408)Claude Code
39dff44afix(ci): isolate live E2E runs and stream RPC diagnostics (#2406)Claude Code
8be8dbdefix(ci): remove RPC provisioning and expose E2E progress (#2405)Claude Code
822b3a28docs: document the long-running (deep-research) cassette re-record recipe Gemini CLI
3fd8f9acfix(review): cover notebook service import guards (#693)Gemini CLI
43220fc2chore(tests): drop internal audit IDs from test docstrings and comments (PGemini CLI
f59ab35afeat(mcp): source_delete accepts multiple sources (bulk) (#1995) (#2262)Cursor Agent

What was excluded

Commits in window	2,043
Merge commits removed	−143
CI / dependency bots removed	−34
Considered	1,866

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 teng-lin/notebooklm-py

Scan another repository

Try