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.

Incremental engine for long horizon agents 🌟 Star if you like it!

cocoindex-io/cocoindex ↗

cocoindex-io/cocoindex AI coding statistics: 42.2%

of 571 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
42.2% agent · top contributor 66.8%15 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

241
agent commits
330
other considered commits
15
agent contributors
66.8%
largest contributor

What shapes this result

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

Assisted or autonomous

240assisted
1autonomous

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
2026-010%1
2026-020%92
2026-038.6%58
2026-0455.9%102
2026-0530.5%82
2026-0667.1%149
2026-0759.2%49
2026-0869.2%13
2026-0964%25

Peak month: 69.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic24042%
Cursor AgentAnysphere10.2%

Inspect the matches

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

Matched commit samples

  • 63d0869d on GitHubfix(engine): reuse a concurrent same-key run's memo instead of re-executinClaude Code
  • dc252bbd on GitHubrefactor(target): fulfill child target providers through per-action child Claude Code
  • 86519a15 on GitHubtest(sdk): serialize deadline tests that share the global test clock (#241Claude Code
  • 6f87f8dc on GitHubfix(localfs): add periodic rescan + watcher recreation for live mode (#223Cursor Agent

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 window629
Merge commits removed−18
CI / dependency bots removed−40
Considered571

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

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 cocoindex-io/cocoindex

Scan another repository