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.

Design database schemas as ERDs in your browser, VS Code, JetBrains IDEs or Obsidian. Import SQL, DBML and GraphQL, export DDL and code, and let coding agents edit live over MCP.

01Result

dineug/erd-editor ↗

dineug/erd-editor AI coding statistics: 83.4%

of 205 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
83.4% agent · top contributor 87.1%2 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

171
agent commits
34
other considered commits
2
agent contributors
87.1%
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

171assisted
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
2026-060%2
2026-0879.3%150
2026-0998.1%53

Peak month: 98.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic16882%
OpenAI CodexOpenAI31.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • b79bc372 on GitHubfix(erd-editor): Keep a Flow view on its last landing until the next one lClaude Code
  • f03d98ff on GitHubfix(erd-editor): Hold a dragged graph dot on the pointer, and reopen its pClaude Code
  • 684f20d2 on GitHubfix(erd-editor): Snap the held row to its slot in the column order and indClaude Code
  • 8f177fc4 on GitHubdocs: Refresh AGENTS.md hierarchyOpenAI Codex
  • e13bd59c on GitHubrefactor(config): derive library settings from package inputsOpenAI Codex
  • 6b98c190 on GitHubdocs: Refresh AGENTS.md against the current treeOpenAI Codex

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 window214
Merge commits removed−9
CI / dependency bots removed−0
Considered205

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 dineug/erd-editor

Scan another repository

Try