- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
An implementation of GitHub's Primer Design System using React
01Result
primer/react ↗primer/react AI coding statistics: 45.4%
Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
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 | 25.6% | 39 |
| 2026-03 | 36.5% | 63 |
| 2026-04 | 36% | 50 |
| 2026-05 | 40.4% | 47 |
| 2026-06 | 57.7% | 78 |
| 2026-07 | 59.4% | 64 |
| 2026-08 | 48.6% | 35 |
| 2026-09 | 50% | 16 |
Peak month: 59.4%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| GitHub Copilot | GitHub | 178 | 45.4% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
29535649on GitHubrefactor(test): migrate to Vitest 5 (#8381)GitHub Copilot6c645987on GitHubDataTable: Add config-driven row groups (#8386)GitHub Copilot35d4a04eon GitHubFix issue-triage.lock.yml workflow failure: remove invalid id-token permisGitHub 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 window | 542 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −150 |
| Considered | 392 |
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 primer/react