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.

Terraform Pull Request Automation

01Result

runatlantis/atlantis ↗

runatlantis/atlantis AI coding statistics: 29.7%

of 172 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
29.7% agent · top contributor 33.3%23 contributors
org-wide

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

51
agent commits
121
other considered commits
23
agent contributors
33.3%
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

51assisted
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
2026-0263.6%11
2026-0345.5%11
2026-0431.4%35
2026-0533.3%12
2026-0626.2%65
2026-078.3%12
2026-0820%10
2026-0925%16

Peak month: 63.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub3118%
Claude CodeAnthropic2112.2%
OpenAI CodexOpenAI10.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 984bd5a4 on GitHubfeat: add --plan-store-dir to decouple plan file storage from data-dir (#6GitHub Copilot
  • 9c57b5f0 on GitHubfeat: workspace detection for .tofu/.tofu.json, shared project indicators GitHub Copilot
  • c34b45e0 on GitHubfix(bitbucket): validate pagination next URLs (#6260)GitHub Copilot
  • 9880b8e8 on GitHubdocs: translate the blog and contributor pages too (#6867)Claude Code
  • 936be75f on GitHubci: lint every translated page and fold serializer-split image links (#686Claude Code
  • 74c7fe9d on GitHubci: make translate-docs incremental and quarantine lint failures (#6864)Claude Code
  • b9b90f24 on GitHubtest(events): cover parallel project command execution (#6469)OpenAI Codex

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 window436
Merge commits removed−0
CI / dependency bots removed−264
Considered172

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 runatlantis/atlantis

Scan another repository

Try