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.

Lock, Stock, and Two Smoking MicroVMs. Create and manage the lifecycle of MicroVMs backed by containerd.

01Result

liquidmetal-dev/flintlock ↗

liquidmetal-dev/flintlock AI coding statistics: 31.6%

of 38 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

Too little recent activity to publish. Only 38 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.

31.6% agent · top contributor 91.7%2 contributors

individual

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

agent commits

other considered commits

agent contributors

91.7%

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

11assisted

1autonomous

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

Peak month: 55.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	8	21.1%
GitHub Copilot	GitHub	4	10.5%

03Evidence

Inspect the matches

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

Matched commit samples

aaa72179 on GitHubfeat(lint): add incremental lint-new target (#1202)Claude Code
47cfc542 on GitHubfeat: execute commands and proxy ssh into a microvm via the guest-agent (#Claude Code
df2f8f9f on GitHubdocs: refresh README badgesClaude Code
c23effc3 on GitHubPotential fix for pull request findingGitHub Copilot
ebf63986 on GitHubPotential fix for pull request findingGitHub Copilot
b2036e50 on GitHubFix proto-lint help text typoGitHub 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 window	70
Merge commits removed	−10
CI / dependency bots removed	−22
Considered	38

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 →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 liquidmetal-dev/flintlock

Scan another repository

Try

Month	Agent share	Considered commits
2026-07	55.6%	9
2026-09	24.1%	29