17.2%

of 2,421 commits were committed by an AI agent — a floor, not an estimate

17.2% agent · top contributor 79.6%31 contributors

team

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

417

agent commits

2,004

human commits

agent contributors

79.6%

largest contributor

Assisted or autonomous

416assisted

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

Peak month: 64.3%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code	Anthropic	406	16.8%
GitHub Copilot	GitHub	13	0.5%
Cursor Agent	Anysphere	3	0.1%

Verify it yourself

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

5419c021fix(runtime): bridge console to the inspector regardless of --inspect flagClaude Code
70dba84cfix(canvas): don't hold SurfaceData mut borrow over window resize (#35993)Claude Code
71289527fix(ext/node): don't schedule a pause in inspector.waitForDebugger() (#357Claude Code
54a12b8afix(ext/node): add `limits` property on `node:sqlite` DatabaseSync (#33106GitHub Copilot
81790b05perf: optimize worker and MessagePort message passing (#32657)GitHub Copilot
c09b7f45fix(ext/web): handle null options in removeEventListener (#32605)GitHub Copilot
90760e7bperf(ext/node): remove per-chunk copying on TLSWrap data paths (#35705)Cursor Agent
aa1380b1perf(ext/node): zero-copy async Buffer writes on the stream_wrap path (#35Cursor Agent
45f999d1fix(ext/node): mark TLSWrap dead on teardown before tls_conn check (#35706Cursor Agent

What was excluded

Commits in window	2,432
Merge commits removed	−0
CI / dependency bots removed	−11
Considered	2,421

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 denoland/deno

Scan another repository

Try