- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
📺 Homebrew's official macOS GUI
01Result
Homebrew/BrewUI ↗Homebrew/BrewUI AI coding statistics: 48.5%
One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
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
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-03 | 0% | 35 |
| 2026-04 | 0% | 80 |
| 2026-05 | 39% | 287 |
| 2026-06 | 58.5% | 130 |
| 2026-07 | 65.8% | 149 |
| 2026-08 | 79.5% | 83 |
| 2026-09 | 64.1% | 117 |
Peak month: 79.5%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 392 | 44.5% |
| GitHub Copilot | GitHub | 23 | 2.6% |
| Cursor Agent | Anysphere | 12 | 1.4% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
7357a220on GitHubScope the ⌘R doctor re-check to the Doctor screenClaude Codeb66d96f7on GitHubWait for a readiness signal instead of a wall clock in the dedup testClaude Code9eb829faon GitHubCut the branch's comments back to what the code cannot sayClaude Code2e05e9ebon GitHubUpdate outdated commentGitHub Copilot2a8867c9on GitHubAdd Brewfile to pathsGitHub Copilot5a226b30on GitHubInstall mintGitHub Copilot2a98734don GitHubSpeed up BrewUILint CI and document local caching.Cursor Agentcabdd688on GitHubFix BrewUILint CI step for macOS Bash 3.2.Cursor Agent7e9ef0c6on GitHubMatch PackageIDRule only on types ending with Package.Cursor Agent
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 window | 1,095 |
| Merge commits removed | −167 |
| CI / dependency bots removed | −47 |
| Considered | 881 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
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 Homebrew/BrewUI