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.

Gajae Code MVP

01Result

Yeachan-Heo/gajae-code ↗

Yeachan-Heo/gajae-code AI coding statistics: 1.5%

of 7,733 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.5% agent · top contributor 24.3%23 contributors
org-wide

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

115
agent commits
7,618
other considered commits
23
agent contributors
24.3%
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

115assisted
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
2026-050%211
2026-060.6%903
2026-070.8%1780
2026-080.9%3860
2026-096.1%979

Peak month: 6.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1141.5%
DevinCognition10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 74341a27 on GitHubdocs(changelog): record the narrowed first-turn retry gatingClaude Code
  • 77eadb0c on GitHubfix(acp): treat session/delete during the retry backoff as voluntary teardClaude Code
  • d0b32579 on GitHubfix(acp): let the first-turn retry wait out the failed attempt's publicatiClaude Code
  • f8dcb2d4 on GitHubfix(coding-agent): skip auto-maintenance when every reachable model is ageDevin

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 window9,076
Merge commits removed−1,343
CI / dependency bots removed−0
Considered7,733

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 →Devin commitsBrowse repositories with detected Devin 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 Yeachan-Heo/gajae-code

Scan another repository

Try