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.

The open-source solution to building, maintaining, and collaborating on GraphQL Federation at Scale. The alternative to Apollo Studio and GraphOS.

01Result

wundergraph/cosmo ↗

wundergraph/cosmo AI coding statistics: 4%

of 649 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
4% agent · top contributor 46.2%9 contributors
org-wide

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

26
agent commits
623
other considered commits
9
agent contributors
46.2%
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

26assisted
0autonomous

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
2026-029%78
2026-034%124
2026-043.4%87
2026-054.8%84
2026-060%92
2026-074.1%97
2026-082.1%48
2026-095.1%39

Peak month: 9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic264%

03Evidence

Inspect the matches

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

Matched commit samples

  • 4d394c48 on GitHubci: replace custom node setup action with pnpm/setup (#3206)Claude Code
  • 7f098487 on GitHubdocs(security): add response time expectations to security policy (#3209)Claude Code
  • b0f5a1b0 on GitHubfix(router): close Kafka consumer client when subscription ends (#3133)Claude Code

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 window654
Merge commits removed−0
CI / dependency bots removed−5
Considered649

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 wundergraph/cosmo

Scan another repository

Try