Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Run your dbt (Core, Fusion, OSS) projects as Apache Airflow DAGs and Task Groups with a few lines of code

01Result

astronomer/astronomer-cosmos ↗

astronomer/astronomer-cosmos AI coding statistics: 53.1%

of 375 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
53.1% agent · top contributor 39.2%17 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

199
agent commits
176
other considered commits
17
agent contributors
39.2%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

196assisted
3autonomous

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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-026.1%66
2026-0325.9%54
2026-0460.8%51
2026-0573.3%75
2026-0673.6%72
2026-0779.5%39
2026-0866.7%15
2026-0933.3%3

Peak month: 79.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic18248.5%
GitHub CopilotGitHub338.8%
Cursor AgentAnysphere20.5%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • e99927c3 on GitHubFix bare selector root resolution under LoadMode.DBT_MANIFEST (#2978)Claude Code
  • f0b3ab83 on GitHubFix AttributeError masking the real dbt error on run-operation failure (#2Claude Code
  • 95c14230 on GitHubRaise minimum supported dbt-core version to 1.8 (#2939)Claude Code
  • ff6b4954 on GitHubHonour dbt test `operator_kwargs` under `TestBehavior.AFTER_EACH` (#2936)GitHub Copilot
  • d8cd3e31 on GitHubDocument verified Cosmos/Runtime/dbt Core compatibility (#2914)GitHub Copilot
  • c531ee20 on GitHubSupport lists of paths for ProjectConfig relative-path args (#2875)GitHub Copilot
  • 63714cdf on GitHub[Experimental feature] enable orjson parser for whole project (#2552)Cursor Agent
  • 4d86173d on GitHubFix KeyError in graph selector when using + operator with dbt-loom ex… (#2Cursor Agent

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 window460
Merge commits removed−0
CI / dependency bots removed−85
Considered375

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Python AI coding statisticsCompare evidence across Python repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

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 astronomer/astronomer-cosmos

Scan another repository

Try