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

pybind/pybind11 ↗

pybind/pybind11 AI coding statistics: 11.6%

of 86 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
Too little recent activity to publish. Only 86 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.
11.6% agent · top contributor 60%5 contributors
team

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

10
agent commits
76
other considered commits
5
agent contributors
60%
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

10assisted
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
2026-01100%1
2026-0225%12
2026-037.1%14
2026-040%7
2026-0545.5%11
2026-060%9
2026-070%16
2026-080%12
2026-090%4

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

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere89.3%
Claude CodeAnthropic22.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 81817aed on GitHubci: remove the deadsnakes job (#6052)Cursor Agent
  • 9cc298a4 on GitHubci: pass explicit ARM64 Python artifacts on windows-11-arm (#6051)Cursor Agent
  • c5b3ae81 on GitHubci: pin PyPy 3.11 to 7.3.21 on macOS and Windows (#6050)Cursor Agent
  • 46ebf503 on GitHubfeat(subinterpreter): reusable PyThreadState via subinterpreter_thread_staClaude Code
  • e7754de0 on GitHubRevert internals destruction and add test for internals recreation (#5972)Claude Code

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 window106
Merge commits removed−0
CI / dependency bots removed−20
Considered86

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
pybind/pybind11
Default branch
master
Resolved HEAD
63121f7b01c88717971233a3937e8869c2947c57 ↗
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.

CohortC/C++ · 127 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 51 of 178 ecosystem repositories excluded
Comparison withheld for low activity

This observation does not meet the 100-commit publication threshold. The cohort definition and sample size remain visible so the omission is auditable.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code 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 pybind/pybind11

Scan another repository

Try