- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Scalable KanColle browser and tool.
01Result
poooi/poi ↗poooi/poi AI coding statistics: 26.7%
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 |
|---|---|---|
| 2026-02 | 0% | 7 |
| 2026-03 | 0% | 3 |
| 2026-04 | 0% | 43 |
| 2026-05 | 0% | 89 |
| 2026-06 | 0% | 24 |
| 2026-07 | 46.9% | 49 |
| 2026-08 | 60.3% | 73 |
| 2026-09 | 52.6% | 38 |
Peak month: 60.3%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 85 | 26.1% |
| GitHub Copilot | GitHub | 2 | 0.6% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
50526ed3on GitHubfix(quest): reject goal files that are not a table of questsClaude Codec2ff08eeon GitHubfix(tab-area): key active plugin lookup by idClaude Code013c81dcon GitHubfeat(quest): track one-time questsClaude Code920d7945on GitHubWarn users running translated ARM builds (#2659)GitHub Copilot1df0bc26on GitHubSkip OpenCode review for non-write actors (#2658)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 | 383 |
| Merge commits removed | −57 |
| CI / dependency bots removed | −0 |
| Considered | 326 |
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 poooi/poi