← the index
docling-project/docling ↗
6.3%
of 491 commits were committed by an AI agent — a floor, not an estimate
6.3% agent · top contributor 19.4%19 contributors
org-wide

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

31
agent commits
460
human commits
19
agent contributors
19.4%
largest contributor

Assisted or autonomous

31assisted
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: 12.2%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic275.5%
GitHub CopilotGitHub30.6%
Cursor AgentAnysphere10.2%

Verify it yourself

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

  • 19ea044bfix(pptx): keep EMF/WMF pictures instead of dropping them (#4089)Claude Code
  • feb0f26bfeat: default to threaded docling-parse across SDK, CLI, service, and extrClaude Code
  • df0e1e1ftest: regression for #3839 (rotated OCR text dropped as furniture) (#3999)Claude Code
  • f2834848fix: handle empty CSV file without crashing (#3196)GitHub Copilot
  • e36125bafix(omml): correct LaTeX output for fractions, math operators, and functioGitHub Copilot
  • 90d6dd4efix(docx): split multiple OMML equations into separate formula items (#312GitHub Copilot
  • 46763a19docs(cli): clarify help text (#3408)Cursor Agent

What was excluded

Commits in window555
Merge commits removed−0
CI / dependency bots removed−64
Considered491

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 docling-project/docling

Scan another repository

Try