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.

Grafana Mimir provides horizontally scalable, highly available, multi-tenant, long-term storage for Prometheus.

01Result

grafana/mimir ↗

grafana/mimir AI coding statistics: 6.9%

of 1,220 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
6.9% agent · top contributor 15.5%30 contributors
org-wide

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

84
agent commits
1,136
other considered commits
30
agent contributors
15.5%
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

77assisted
7autonomous

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
2026-029%145
2026-034.2%212
2026-045.4%147
2026-0510.3%156
2026-064.6%219
2026-078.9%180
2026-088.6%116
2026-094.4%45

Peak month: 10.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic504.1%
Cursor AgentAnysphere352.9%
GitHub CopilotGitHub20.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • b464e5d6 on GitHub[main] Update mimir-prometheus to 544b719f1ae3 (#16568)Claude Code
  • 41afd380 on GitHub[main] Update mimir-prometheus to 7d14de8bd099 (#16560)Claude Code
  • 1bbffa50 on GitHubBlock-builder: fix silent data loss for single-record jobs (#16493)Claude Code
  • 1bbffa50 on GitHubBlock-builder: fix silent data loss for single-record jobs (#16493)Cursor Agent
  • b841a119 on GitHubMove binary operation matcher propagation from frontend middleware into ASCursor Agent
  • 5b72e3ec on GitHubUpdate warpstream-go to latest main (#16304)Cursor Agent
  • 771f9ca0 on GitHubmimirpb: separate FloatSample (read path) from Sample (write path) (#16278GitHub Copilot
  • afb9f0c5 on GitHubusage-tracker: flaky test improvements. (#14574)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 window1,775
Merge commits removed−53
CI / dependency bots removed−502
Considered1,220

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 grafana/mimir

Scan another repository

Try