- Dataset
- 2026-09-18-v3.0
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-09-16
- Window
- February–September 15, 2026
01Result
apache/airflow ↗apache/airflow AI coding statistics: 3.5%
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 |
|---|---|---|
| 2026-01 | 0% | 1 |
| 2026-02 | 4.2% | 566 |
| 2026-03 | 6.6% | 894 |
| 2026-04 | 3% | 689 |
| 2026-05 | 2.9% | 679 |
| 2026-06 | 3.4% | 682 |
| 2026-07 | 1.9% | 731 |
| 2026-08 | 1.8% | 556 |
| 2026-09 | 2.5% | 322 |
Peak month: 6.6%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 123 | 2.4% |
| GitHub Copilot | GitHub | 37 | 0.7% |
| Cursor Agent | Anysphere | 21 | 0.4% |
| Devin | Cognition | 1 | 0% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
4e52a36eon GitHubAllow opting into fork+exec task processes via execute_tasks_new_python_inClaude Code2bb32e37on GitHubStop swallowing unexpected keyring errors when saving airflowctl credentiaClaude Code1685bd6fon GitHubRun short CI bookkeeping jobs on ubuntu-slim runners (#72852)Claude Coded0577848on GitHubFix DeadlockImminentError when a connection is resolved inside an async taGitHub Copilotf558ff13on GitHubStop discarding a MeterProvider configured via OTEL_CONFIG_FILE (#71529)GitHub Copilotf0c13dc5on GitHubFix task callbacks being skipped when `TriggerDagRunOperator` gets a 404 (GitHub Copilotb3b62fa8on GitHubAdd unit tests for common AI provider exceptions (#72082)Cursor Agent5dcee049on GitHubAdd warning for HttpOperator deferrable with non-idempotent methods (#6974Cursor Agentc4e6ed36on GitHubAdd deferrable mode to Databricks SQL warehouse operators (#71752)Cursor Agentb21e4299on GitHubMigrate Airbyte provider to `airbyte-api` library 1.0 and `httpx` (#68882)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 | 5,477 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −357 |
| Considered | 5,120 |
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
- apache/airflow
- Default branch
- main
- Resolved HEAD
- ebd339fa6202a8d100c18f0fc7b21876c992e515 ↗
- 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
- 3.5%
- Cohort median
- 6.3%
- Share rank
- 157 / 247
Percentile = (repositories below + half of 2 tied repositories) ÷ 247.
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 apache/airflow