Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

huggingface/sentence-transformers ↗

huggingface/sentence-transformers AI coding statistics: 2.8%

of 645 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.8% agent · top contributor 38.9%10 contributors
org-wide

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

18
agent commits
627
other considered commits
10
agent contributors
38.9%
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

18assisted
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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-025.1%39
2026-030%142
2026-042.9%103
2026-053.8%26
2026-069.4%53
2026-071.4%141
2026-085.1%99
2026-090%42

Peak month: 9.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub162.5%
Claude CodeAnthropic30.5%
Cursor AgentAnysphere10.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1f3babf8 on GitHubdocs: Align MultiVectorEncoder pages with the other archetypes (#3933)GitHub Copilot
  • f35b1468 on GitHub[`v6`] fix: upcast cross-encoder logits to float32 before activation (HPS)GitHub Copilot
  • f1dc93fb on GitHub[`v6`] fix: compute similarity scores in float32 to avoid low-precision tiGitHub Copilot
  • f35b1468 on GitHub[`v6`] fix: upcast cross-encoder logits to float32 before activation (HPS)Claude Code
  • f1dc93fb on GitHub[`v6`] fix: compute similarity scores in float32 to avoid low-precision tiClaude Code
  • 99b0a84c on GitHub[fix] Detach KL teacher & fix per-layer weighting in AdaptiveLayerLoss (#3Claude Code
  • d2ac5044 on GitHub[`fix`] `GroupByLabelBatchSampler` to guarantee multi-class batches for trCursor 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 window670
Merge commits removed−15
CI / dependency bots removed−10
Considered645

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

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
huggingface/sentence-transformers
Default branch
main
Resolved HEAD
4e1fb7221a5097a03e281ca1a42525c396c3acb2 ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position33rd percentile

Midrank percentile; equal shares split the tied positions.

Repository
2.8%
Cohort median
6.3%
Share rank
165 / 247
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 247.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 huggingface/sentence-transformers

Scan another repository

Try