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.

Nix packages for AI coding agents and development tools. Automatically updated daily.

numtide/llm-agents.nix ↗

numtide/llm-agents.nix AI coding statistics: 17.9%

of 1,025 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
17.9% agent · top contributor 29.5%21 contributors
org-wide

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

183
agent commits
842
other considered commits
21
agent contributors
29.5%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

154assisted
29autonomous

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
2026-0237%73
2026-033.9%129
2026-0414.9%148
2026-0526.5%136
2026-0617.9%95
2026-0711.7%154
2026-0822.7%203
2026-0913.8%87

Peak month: 37%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic16516.1%
GitHub CopilotGitHub181.8%

Inspect the matches

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

Matched commit samples

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 window14,291
Merge commits removed−6,793
CI / dependency bots removed−6,473
Considered1,025

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

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 numtide/llm-agents.nix

Scan another repository