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.

AgentENV (AENV) is a distributed platform for running agent environments at scale.

01Result

kvcache-ai/AgentENV ↗

kvcache-ai/AgentENV AI coding statistics: 8.9%

of 192 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
8.9% agent · top contributor 58.8%5 contributors
team

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

17
agent commits
175
other considered commits
5
agent contributors
58.8%
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

17assisted
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
2026-075.6%36
2026-0812.6%111
2026-092.2%45

Peak month: 12.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic147.3%
GitHub CopilotGitHub31.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 0d9027e3 on GitHubfix(template): report failed build steps by number, not instruction text (Claude Code
  • e97064f4 on GitHubfix(overlaybd): reject unaligned extents when scanning a sparse sourceClaude Code
  • 3522df87 on GitHubfeat(overlaybd): reject the sparse upper layout on macOSClaude Code
  • d2405769 on GitHubtest(resolver): locate fake regctl fixtures relative to $0GitHub Copilot
  • fa4d8867 on GitHubtest(resolver): correct multi-referrer comment to match resolver behaviourGitHub Copilot
  • a7233324 on GitHubfeat(image): discover ACR artifact streaming overlaybd referrersGitHub 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 window192
Merge commits removed−0
CI / dependency bots removed−0
Considered192

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 →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Rust AI coding statisticsCompare evidence across Rust 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 kvcache-ai/AgentENV

Scan another repository

Try