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 Feature Store for AI/ML

01Result

feast-dev/feast ↗

feast-dev/feast AI coding statistics: 12.9%

of 410 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
12.9% agent · top contributor 15.1%24 contributors
org-wide

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

53
agent commits
357
other considered commits
24
agent contributors
15.1%
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

53assisted
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
2026-0219.4%36
2026-0313.4%67
2026-0416.7%66
2026-057%57
2026-066.3%63
2026-0718.8%69
2026-088.9%45
2026-0914.3%7

Peak month: 19.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic256.1%
Cursor AgentAnysphere163.9%
GitHub CopilotGitHub71.7%
DevinCognition61.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • b5090c6c on GitHubci: Pin CPU-only torch and bound floating dependencies (#6825)Claude Code
  • 79b33ce4 on GitHubfeat: Add opt-in filter_by_created_timestamp cutoff to get_historical_featClaude Code
  • 43ae9933 on GitHubfeat: Apply Intermediate TLS defaults on API fallback and handle transientClaude Code
  • f0bc0700 on GitHubfix: Feature freshness logic updated (#6765)Cursor Agent
  • e79bd331 on GitHubci: Add bundle-sync verification to operator PR workflow (#6751)Cursor Agent
  • 398f6435 on GitHubfix: Separate CronJob and feature-server ServiceAccountsCursor Agent
  • 9cd35e14 on GitHubfeat: Add OnlineStore for Aerospike (#6532)GitHub Copilot
  • bedc0eff on GitHub[WIP] Add hero image for social preview in blog posts (#6379)GitHub Copilot
  • a6236749 on GitHubdocs: Add blog post on experimental feature view versioning support (#6204GitHub Copilot
  • 7c04026a on GitHubfeat: Extended OIDC support to extract groups & namespaces and token injecDevin
  • 9d353682 on GitHubfeat: Add Oracle DB as Offline store in python sdk & operator (#6017)Devin
  • 56469f7d on GitHubfeat: Adding optional name to Aggregation (feast-dev#5994) (#6083)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 window413
Merge commits removed−2
CI / dependency bots removed−1
Considered410

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 →Devin commitsBrowse repositories with detected Devin 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 feast-dev/feast

Scan another repository

Try