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.

Simple key-value storage with support for multiple backends

01Result

jaredwray/keyv ↗

jaredwray/keyv AI coding statistics: 50.5%

of 273 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
50.5% agent · top contributor 99.3%2 contributors
individual

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

138
agent commits
135
other considered commits
2
agent contributors
99.3%
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

138assisted
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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0220%45
2026-037%57
2026-040%22
2026-0514.3%7
2026-0683.3%42
2026-0763%27
2026-0896.7%30
2026-09100%43

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic8531.1%
Cursor AgentAnysphere5118.7%
Gemini CLIGoogle20.7%

03Evidence

Inspect the matches

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

Matched commit samples

  • a3404d35 on GitHubmono - chore: release concurrency group + v5 staged publishing docs (#2124Claude Code
  • fc723000 on GitHubtest-suite - fix: de-flake storage TTL expiry tests (#2040)Claude Code
  • fffd44b9 on GitHubrelease: v6.0.0-rc.1 (#2039)Claude Code
  • 00a48ba9 on GitHubredis - fix: Abort timed-out Redis connects without leaking sockets (#2108Cursor Agent
  • bb35d2b7 on GitHubredis - fix: share in-flight connect so concurrent ops are not dropped (#2Cursor Agent
  • f6622a01 on GitHubmono - chore: defense - drop automatic-tasks manual item (#2104)Cursor Agent
  • e8679aa0 on GitHubkeyv - fix: updating checks for browser tests (#1908)Gemini CLI
  • 99cfbd4c on GitHubcompress-brotli - feat: moving to native zlib brotli engine (#1841)Gemini CLI

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 window274
Merge commits removed−1
CI / dependency bots removed−0
Considered273

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 jaredwray/keyv

Scan another repository

Try