Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Archive a lifetime of email and chat. Offline search, analytics, and AI query over your full message history. Powered by SQLite and DuckDB

01Result

kenn-io/msgvault ↗

kenn-io/msgvault AI coding statistics: 33.6%

of 547 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
33.6% agent · top contributor 73.4%21 contributors
team

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

184
agent commits
363
other considered commits
21
agent contributors
73.4%
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

181assisted
3autonomous

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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-01100%12
2026-0292.7%123
2026-0378.9%19
2026-0455.9%34
2026-0523.7%38
2026-068.3%36
2026-072.7%75
2026-084.5%110
2026-095%100

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic17431.8%
OpenAI CodexOpenAI101.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • f78d4ae6 on GitHubfeat(settings): section the Web Settings page, move limits onto controls, Claude Code
  • 40d223ed on GitHubfix(ci): stop lease renewal deadlock and relax two timing-bound tests (#71Claude Code
  • 3e812e87 on GitHubfix(nix): make the sandboxed web build work on GitHub-hosted runners (#607Claude Code
  • ccead042 on GitHubci: prepare container release artifacts (#846)OpenAI Codex
  • ae02f2d1 on GitHubfix: stabilize header layout and worker renewal test (#818)OpenAI Codex
  • 12b0265d on GitHubfix(slack): keep sweep test burst within one UTC day (#789)OpenAI Codex

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 window580
Merge commits removed−0
CI / dependency bots removed−33
Considered547

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Go AI coding statisticsCompare evidence across Go repositories →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 kenn-io/msgvault

Scan another repository

Try