← the index
firecrawl/pdf-inspector
62.5%
of 509 commits were committed by an AI agent — a floor, not an estimate
62.5% agent · top contributor 77.7%5 contributors
team

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

318
agent commits
191
human commits
5
agent contributors
77.7%
largest contributor

Assisted or autonomous

318assisted
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: 86.5%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic30058.9%
Cursor AgentAnysphere183.5%

Verify it yourself

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

  • 183c5d8cchore(deps): bump lopdf to 0.45.0 (#534)Claude Code
  • 72f7c718feat(positions): add a display frame option to the positioned-text and regClaude Code
  • 6e6a71ccfix(loader): rebuild classic xref tables with 19-byte entries (#508)Claude Code
  • 4bee4f99chore(release): bump package versions to 1.14.2 (#382)Cursor Agent
  • 1719d248fix(tables): bound disjoint-rect clustering so overlap tests stay subquadrCursor Agent
  • f114e79cfix(detector): bound Tj/TJ operand lookback to the previous operator (#380Cursor Agent

What was excluded

Commits in window516
Merge commits removed7
CI / dependency bots removed0
Considered509

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 firecrawl/pdf-inspector

Scan another repository