- Dataset
- 2026-09-18-v3.0
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-09-16
- Window
- February–September 15, 2026
01Result
github/docs ↗github/docs AI coding statistics: 53.8%
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. Across the whole index, 96% of agent commits are assisted.
Agent share by month
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-02 | 34% | 329 |
| 2026-03 | 51.1% | 493 |
| 2026-04 | 47.5% | 360 |
| 2026-05 | 54.8% | 343 |
| 2026-06 | 62.4% | 394 |
| 2026-07 | 71% | 410 |
| 2026-08 | 51% | 343 |
| 2026-09 | 55.4% | 224 |
Peak month: 71%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| GitHub Copilot | GitHub | 1553 | 53.6% |
| Claude Code | Anthropic | 4 | 0.1% |
| Devin | Cognition | 3 | 0.1% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
74c7d20aon GitHubTrim excessive comments in src/frame/middleware (#63259)GitHub Copilote3034ac8on GitHubTrim excessive comments in the rest of src/content-render (#63278)GitHub Copilot20e9ba9eon GitHubTrim excessive comments in src/article-api tests (#63280)GitHub Copilot666fccbaon GitHubSignal that the `copilot-setup-steps.yml` samples are illustrative (#45862Claude Code1f077aa2on GitHubScope `push` to the default branch in copilot-setup-steps samples (#45823)Claude Codedfd306e2on GitHubImprove readability of lowest unmerged pull request condition in stacked PClaude Code89b94425on GitHubPatch release notes for GitHub Enterprise Server (#62578)Devin29dd453con GitHubPatch release notes for GitHub Enterprise Server (#61095)Devinc587f78eon GitHubPatch release notes for GitHub Enterprise Server (#60602)Devin
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 | 3,764 |
| Merge commits removed | −752 |
| CI / dependency bots removed | −116 |
| Considered | 2,896 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
05Provenance
Pinned to a source state
This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.
- Dataset release
- 2026-09-18-v3.0
- Scan date
- 2026-09-16
- Ruleset
- sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
- Canonical repository
- github/docs
- Default branch
- main
- Resolved HEAD
- d79d9d354377b9f8b820e16c12b91734881a0f93 ↗
- Resolved
- 2026-09-16
- Measurement window
- February–September 15, 2026
06Peer context
Position among comparable repositories
The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.
Midrank percentile; equal shares split the tied positions.
- Repository
- 53.8%
- Cohort median
- 5.4%
- Share rank
- 18 / 376
Percentile = (repositories below + half of 2 tied repositories) ÷ 376.
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 github/docs