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

vxcontrol/pentagi ↗

vxcontrol/pentagi AI coding statistics: 67.8%

of 859 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
67.8% agent · top contributor 98.8%4 contributors
individual

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

582
agent commits
277
other considered commits
4
agent contributors
98.8%
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

582assisted
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
2026-030%8
2026-047.2%83
2026-0563.6%228
2026-0673%211
2026-0790.5%306
2026-080%23

Peak month: 90.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic55664.7%
Cursor AgentAnysphere252.9%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • f95c48b0 on GitHubrefactor(knowledges): give knowledgeId back to the route paramClaude Code
  • e51f686e on GitHubrefactor: drop the header-order comment and the rest of the narrationClaude Code
  • f24b75f3 on GitHubrefactor: cut the comments that only explain the authorClaude Code
  • 5319d1cb on GitHubfeat(frontend): unify list tables with URL sync, navigation, and VitestCursor Agent
  • fff79b39 on GitHubfeat(knowledges): inline rename and delete actions in knowledge header andCursor Agent
  • bce4d790 on GitHubfeat(templates): inline rename and delete actions in template header and lCursor Agent
  • de6f527e on GitHubApply suggestions from code reviewGitHub Copilot

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 window938
Merge commits removed−75
CI / dependency bots removed−4
Considered859

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
vxcontrol/pentagi
Default branch
main
Resolved HEAD
ea665308baaff015b226f308438a68d929d0f29b ↗
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.

CohortGo · 132 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 62 of 194 ecosystem repositories excluded
Agent-commit share position98th percentile

Midrank percentile; equal shares split the tied positions.

Repository
67.8%
Cohort median
2.8%
Share rank
3 / 132
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 132.

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 vxcontrol/pentagi

Scan another repository

Try