Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

ccusage/ccusage ↗

ccusage/ccusage AI coding statistics: 3.8%

of 393 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.8% agent · top contributor 80%4 contributors
individual

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

15
agent commits
378
other considered commits
4
agent contributors
80%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

15assisted
0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-020%12
2026-030%13
2026-040%8
2026-053.5%170
2026-060%91
2026-0714.5%55
2026-080%32
2026-098.3%12

Peak month: 14.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic71.8%
Cursor AgentAnysphere71.8%
GitHub CopilotGitHub10.3%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • d3419498 on GitHubfix(claude): keep entries whose usage.iterations[].model is null (#1719)Claude Code
  • 69fbca0f on GitHubfix(kimi): support Kimi Code new wire format (#1362)Claude Code
  • bf84d4bc on GitHubfix(all): collapse per-day rows in monthly/weekly all-agent table (#1148)Claude Code
  • 292e7203 on GitHubfix(progress): keep the spinner status on a single row (#1500)Cursor Agent
  • 473019df on GitHubfeat: add `--last` to report the most recent N periods (#1498)Cursor Agent
  • 86788c3a on GitHubperf(rust): split the workspace into independently cached crates (#1428)Cursor Agent
  • 35e00901 on GitHubfix(cli): normalize since and until date bounds (#1144)GitHub Copilot

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window720
Merge commits removed−0
CI / dependency bots removed−327
Considered393

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
ccusage/ccusage
Default branch
main
Resolved HEAD
5e88263ed3c16cf79b42a71d93139cf17a50921c ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortRust · 117 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 33 of 150 ecosystem repositories excluded
Agent-commit share position63rd percentile

Midrank percentile; equal shares split the tied positions.

Repository
3.8%
Cohort median
2%
Share rank
44 / 117
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 117.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli ccusage/ccusage

Scan another repository

Try