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.

JetBrains Meta programming System

01Result

JetBrains/MPS ↗

JetBrains/MPS AI coding statistics: 10.5%

of 967 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
10.5% agent · top contributor 65.7%5 contributors
team

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

102
agent commits
865
other considered commits
5
agent contributors
65.7%
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

102assisted
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%104
2026-030%96
2026-044.7%171
2026-053.3%151
2026-067.6%119
2026-078.8%114
2026-0823%74
2026-0938.4%138

Peak month: 38.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic767.9%
OpenAI CodexOpenAI282.9%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1e71921d on GitHubMPS-40142 do not run make under a modal progress when requested off the EDClaude Code
  • 55d1e048 on GitHubMPS-40142 evaluate watches directly instead of through a nested invokeLateClaude Code
  • 159731e1 on GitHubMPS-40122 do not compute VCS add-ons state on the caller's threadClaude Code
  • 499c4a0f on GitHubMPS-40142 resolve the evaluation model under a read actionOpenAI Codex
  • 3ad9e9c2 on GitHubMPS-40122 suppress error dialogs during VCS add-ons dry runsOpenAI Codex
  • b26b5f5b on GitHubMPS-40131 fix diff title alignment for added and deleted modelsOpenAI Codex
  • 2eac3cac on GitHubAdd failing test for stub model descriptor publish raceGitHub 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 window1,044
Merge commits removed−77
CI / dependency bots removed−0
Considered967

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 →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 JetBrains/MPS

Scan another repository

Try