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

DeusData/codebase-memory-mcp ↗

DeusData/codebase-memory-mcp AI coding statistics: 5.1%

of 2,213 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.1% agent · top contributor 28.3%26 contributors
org-wide

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

113
agent commits
2,100
other considered commits
26
agent contributors
28.3%
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

113assisted
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
2026-025.6%36
2026-039.7%300
2026-040%101
2026-051.5%204
2026-062.1%373
2026-072.3%597
2026-081.9%429
2026-0928.3%173

Peak month: 28.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1064.8%
Cursor AgentAnysphere70.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 61884951 on GitHubstyle(install): clang-format-20 the LSA helper declarations (#1705)Claude Code
  • df579830 on GitHubfix(install): trust the local machine's built-in Administrator; name untruClaude Code
  • 8116672a on GitHubfix(daemon): accept single-uid userns overflow-owned ancestors (#1830)Claude Code
  • 0106ff5d on GitHubfix(mcp): emit trace evidence columns in header orderCursor Agent
  • 416ba994 on GitHubfix(registry): drop suffix_match CALLS across language boundariesCursor Agent
  • d613840c on GitHubchore: retrigger CI after unrelated macos-15-intel lock_registry flakeCursor Agent

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 window3,036
Merge commits removed−780
CI / dependency bots removed−43
Considered2,213

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
DeusData/codebase-memory-mcp
Default branch
main
Resolved HEAD
59a05eb1bf9e11deb060d782cd7d3a29f2ae2866 ↗
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
Agent-commit share position81st percentile

Midrank percentile; equal shares split the tied positions.

Repository
5.1%
Cohort median
0.4%
Share rank
25 / 127
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 127.

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 DeusData/codebase-memory-mcp

Scan another repository

Try