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

docling-project/docling ↗

docling-project/docling AI coding statistics: 6.3%

of 524 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
6.3% agent · top contributor 18.2%19 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

33
agent commits
491
other considered commits
19
agent contributors
18.2%
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

33assisted
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
2026-027.4%27
2026-038.2%61
2026-0410.6%66
2026-058.9%45
2026-062.2%92
2026-070%99
2026-0812.2%90
2026-094.5%44

Peak month: 12.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic295.5%
GitHub CopilotGitHub30.6%
Cursor AgentAnysphere10.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 5ef4f928 on GitHubfix(html): flag pivot-table row headers as row_header, not column_header (Claude Code
  • 19ea044b on GitHubfix(pptx): keep EMF/WMF pictures instead of dropping them (#4089)Claude Code
  • feb0f26b on GitHubfeat: default to threaded docling-parse across SDK, CLI, service, and extrClaude Code
  • f2834848 on GitHubfix: handle empty CSV file without crashing (#3196)GitHub Copilot
  • e36125ba on GitHubfix(omml): correct LaTeX output for fractions, math operators, and functioGitHub Copilot
  • 90d6dd4e on GitHubfix(docx): split multiple OMML equations into separate formula items (#312GitHub Copilot
  • 46763a19 on GitHubdocs(cli): clarify help text (#3408)Cursor Agent

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 window590
Merge commits removed−0
CI / dependency bots removed−66
Considered524

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
docling-project/docling
Default branch
main
Resolved HEAD
e8c6092fe6ee995ce0719a71352b9f1fad5350cf ↗
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.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position50th percentile

Midrank percentile; equal shares split the tied positions.

Repository
6.3%
Cohort median
6.3%
Share rank
124 / 247
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 247.

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 docling-project/docling

Scan another repository

Try