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

grafana/loki ↗

grafana/loki AI coding statistics: 3.5%

of 1,151 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.5% agent · top contributor 37.5%14 contributors
org-wide

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

40
agent commits
1,111
other considered commits
14
agent contributors
37.5%
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

39assisted
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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-021.3%159
2026-033.5%115
2026-040.7%147
2026-053.9%154
2026-060.6%159
2026-071.2%169
2026-088.5%176
2026-0912.5%72

Peak month: 12.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere201.7%
Claude CodeAnthropic171.5%
GitHub CopilotGitHub30.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 88531532 on GitHubfeat(logline): Split Logline filters into k gap-cut envelopes (#24475)Cursor Agent
  • 4e3fb385 on GitHubfix(operator): Validate passthrough gateway CA exists (#23800)Cursor Agent
  • 48e7ae39 on GitHubfeat(compaction): Merge unique label sets to one global ID during compactiCursor Agent
  • 60a72015 on GitHubfix(querier): Stop reporting a cancelled tail teardown as an error (#24464Claude Code
  • fc848e0c on GitHubfix(otlp): close zstd decoder to prevent goroutine leak (#24356)Claude Code
  • 52c7d20c on GitHubfeat(kafka): Kafka decoders support both formats (#24244)Claude Code
  • b645ac3c on GitHubfeat: Add q param to /config for scoped field access (#24230)GitHub Copilot
  • e90e4a63 on GitHubfeat: early goldfish correlation ID generation with X-Loki-Goldfish-ID heaGitHub Copilot
  • 83e27577 on GitHubchore: bring comparison metrics and goldfish metrics more in line (#20706)GitHub 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 window1,990
Merge commits removed−0
CI / dependency bots removed−839
Considered1,151

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
grafana/loki
Default branch
main
Resolved HEAD
a83281353cf6ce192be30d0d935b53f675a79f66 ↗
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.

CohortGo · 132 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 62 of 194 ecosystem repositories excluded
Agent-commit share position54th percentile

Midrank percentile; equal shares split the tied positions.

Repository
3.5%
Cohort median
2.8%
Share rank
60 / 132
0th50th100th

Percentile = (repositories below + half of 3 tied repositories) ÷ 132.

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 grafana/loki

Scan another repository

Try