- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
shadcn/ui, but for Svelte. ✨
01Result
huntabyte/shadcn-svelte ↗huntabyte/shadcn-svelte AI coding statistics: 12.6%
A small group is using agents. Adoption has spread beyond one person but is not project-wide.
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 |
|---|---|---|
| 2026-02 | 0% | 8 |
| 2026-03 | 0% | 22 |
| 2026-04 | 22.7% | 22 |
| 2026-05 | 22.2% | 9 |
| 2026-06 | 22.2% | 9 |
| 2026-07 | 5.6% | 18 |
| 2026-08 | 16.7% | 6 |
| 2026-09 | 22.2% | 9 |
Peak month: 22.7%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 11 | 10.7% |
| GitHub Copilot | GitHub | 2 | 1.9% |
| Cursor Agent | Anysphere | 1 | 1% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
7f5289a7on GitHubparity: select (#2883)Claude Codedabbd4c0on GitHubfeat: migrate data tables to TanStack Table v9 (#2840)Claude Codec6bf7d5bon GitHubfix(cli): resolve nearest tsconfig/jsconfig during init (#2806)Claude Code1c6bc548on GitHubchore: update workflows (#2630)GitHub Copilot3b62d91fon GitHubfix: repro (#2631)GitHub Copilot4c6406f1on GitHubparity checker cli (#2876)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 | 124 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −21 |
| Considered | 103 |
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 huntabyte/shadcn-svelte