- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Distributed, offline-first bug tracker integrated in git
01Result
git-bug/git-bug ↗git-bug/git-bug AI coding statistics: 65.9%
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 | 76.1% | 71 |
| 2026-04 | 90.8% | 98 |
| 2026-05 | 0% | 21 |
| 2026-06 | 0% | 8 |
| 2026-09 | 0% | 19 |
Peak month: 90.8%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 141 | 65% |
| GitHub Copilot | GitHub | 2 | 0.9% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
a96414e6on GitHubfix(web): resolve remaining non-story lint warningsClaude Code61e7ff46on GitHubfix(web): resolve fragment masking type warnings in routes and authClaude Code558ddfbaon GitHubrefactor(web): switch to codegen useFragment, fix storybook + typesClaude Codebbe521e5on GitHubgraphql: replace GitRef.isDefault by Repository.head (#1551)GitHub Copilot66f1bc37on GitHubgraphql: replace GitRef.isDefault by Repository.head (#1551)GitHub 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 | 241 |
| Merge commits removed | −21 |
| CI / dependency bots removed | −3 |
| Considered | 217 |
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 git-bug/git-bug