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.

The World's First Virtual Terminal for AI Agents

01Result

strukto-ai/mirage ↗

strukto-ai/mirage AI coding statistics: 15.3%

of 2,149 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
15.3% agent · top contributor 45.9%12 contributors
org-wide

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

329
agent commits
1,820
other considered commits
12
agent contributors
45.9%
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

329assisted
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
2026-052.4%164
2026-063.2%598
2026-0712.9%279
2026-0826.4%628
2026-0921.7%480

Peak month: 26.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic32715.2%
Cursor AgentAnysphere10%
GitHub CopilotGitHub10%

03Evidence

Inspect the matches

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

Matched commit samples

  • fca4de3c on GitHubci: diff-scope the pre-commit hooks, drop two duplicate whole-repo runsClaude Code
  • b6466b8a on GitHubCatch a simple flag dest too, by naming the raw bag `bag`Claude Code
  • 0f8973a8 on GitHubfix(commands): match GNU semantics across nine py/ts command divergencesClaude Code
  • 06f30ebb on GitHubfix: use Dropbox list_folder/continue behind watch pullCursor Agent
  • 3b18a436 on GitHubrefactor(runtime): one mount op vocabulary for the typescript sandbox runtGitHub 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 window2,642
Merge commits removed−474
CI / dependency bots removed−19
Considered2,149

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 strukto-ai/mirage

Scan another repository

Try