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

apache/spark ↗

apache/spark AI coding statistics: 0.6%

of 3,267 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
0.6% agent · top contributor 78.9%3 contributors
individual

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

19
agent commits
3,248
other considered commits
3
agent contributors
78.9%
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

19assisted
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
2026-020.3%382
2026-030%383
2026-040%335
2026-050%371
2026-060%491
2026-070.4%535
2026-080.2%522
2026-096%248

Peak month: 6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere160.5%
Claude CodeAnthropic50.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 73b245fe on GitHub[PYTHON][MINOR] Use a unique per-run rendezvous id for distributed torch tCursor Agent
  • ef6f78bc on GitHub[SQL][MINOR] Bound nesting depth when converting protobuf Any to JSONCursor Agent
  • ca8e43ba on GitHub[MINOR] Improve resilence on raw socket stream and steer people towards hiCursor Agent
  • ca8e43ba on GitHub[MINOR] Improve resilence on raw socket stream and steer people towards hiClaude Code
  • 77f1e057 on GitHub[PYTHON][MINOR] Improve TorchDistributor log server provisioningClaude Code
  • 432adc74 on GitHub[MINOR][UI] Escape HTML when rendering error messages in the Web UI tablesClaude 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 window3,267
Merge commits removed−0
CI / dependency bots removed−0
Considered3,267

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
apache/spark
Default branch
master
Resolved HEAD
89c694a84d7435cabe3590302ae00a9f92047644 ↗
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.

CohortScala · 2 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 1 of 3 ecosystem repositories excluded
Comparison withheld for a small cohort

Only 2 eligible repositories remain; qmmit requires at least 10 before showing a percentile. 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 apache/spark

Scan another repository

Try