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.

A framework for few-shot evaluation of language models.

01Result

EleutherAI/lm-evaluation-harness ↗

EleutherAI/lm-evaluation-harness AI coding statistics: 5.1%

of 178 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.1% agent · top contributor 22.2%8 contributors
team

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

9
agent commits
169
other considered commits
8
agent contributors
22.2%
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

9assisted
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
2026-020%22
2026-030%17
2026-0416.7%12
2026-053.6%28
2026-060%11
2026-0733.3%3
2026-084.1%73
2026-0916.7%12

Peak month: 33.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic84.5%
Cursor AgentAnysphere10.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • e54687ea on GitHubfix(bbh): guard find_match against an all-empty capture tuple (#4125)Claude Code
  • 69c005f2 on GitHubfeat(registry): runtime plugin registration for model backends (#4013)Claude Code
  • b0195a94 on GitHubfeat(models): add cross-platform onnxruntime-genai backend + refactor winmClaude Code
  • 4b6c8f16 on GitHubfix(tasks): use namespaced dataset paths for xnli/xcopa/paws-x/xquad (#387Cursor Agent

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 window178
Merge commits removed−0
CI / dependency bots removed−0
Considered178

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 →Python AI coding statisticsCompare evidence across Python 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 EleutherAI/lm-evaluation-harness

Scan another repository

Try