Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
Assisted or autonomous
Assisted — a developer’s identity authored the commit and the agent added itself as co-author. The agent ran git commit during a working session, with a person there. Autonomous — a bot identity is the author, no human in the loop. Across the whole index, 93.7% of agent commits are assisted.
Agent share by month
Peak month: 42.2%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 1697 | 11.8% |
| Cursor Agent | Anysphere | 1583 | 11% |
| GitHub Copilot | GitHub | 250 | 1.7% |
| OpenAI Codex | OpenAI | 3 | 0% |
| Devin | Cognition | 3 | 0% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
2bd896a2[Agent Builder] Introduce Event type registry (#290151)Claude Code6ad44bb1[Agent Builder] Exclude jina-ocr-v1 from LLM converse smoke tests (#291200Claude Codea4346aeaResolve user settings once per page render (#291066)Claude Codea7be4c3c[Discover] Show where to add METADATA when an ES|QL result cannot be shareCursor Agent9102ab37[Alerting] Rename Execution history Policies tab to Action policies (#2909Cursor Agent03c4a447[DOCS] Note Dashboards listing cap on savedObjects:listingLimit (#291221)Cursor Agentcd70c1a7[Synthetics] Fix flaky OverviewCompactView by seeding monitor before navigGitHub Copilot114098eeHide deactivated-user activation action for read-only users (#289801)GitHub Copilot6060e01e[EDR Workflows][Custom YARA signatures] Add internal `_validate` API (#287GitHub Copilot279e75ac[Console] Support auto-indenting requests with comments (#284527)OpenAI Codex8935d6d8[Index Management] Fix flaky mapper-size plugin test by moving coverage toOpenAI Codex04e046ce[Ingest Pipelines] Give Processor: Fail beforeEach hook timeout headroom (OpenAI Codexdfc3f90f[Security]: migrate StepAboutRule unit tests from Enzyme to @testing-libraDevinc5f74d22[Security Solution][Detection Engine] updates AI rule creation workflow (#Devina6b9d4b7[Security Solution] Adjust log level and wording of logs written from ruleDevin
What was excluded
| Commits in window | 14,671 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −311 |
| Considered | 14,360 |
Bots are excluded from the denominator entirely. Counting dependabot as “AI-written code” is the fastest way to produce a meaningless number.
How this was measured
Measured over February–August 2026, cloned directly. Detection is deterministic string matching against signatures agents write about themselves — no heuristics, no style analysis. Merge commits and CI bots are excluded from the denominator. The figure is a floor: squash merges strip trailers, so real usage is higher. Contributor counts are aggregate — no individual is named.
Run it yourself: npx qmmit-cli elastic/kibana