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.

Open-source desktop SQL workspace with 3 built-in database drivers and 24 shipped driver plugins, including SQL Server, DuckDB, ClickHouse and Redis. Built-in MCP server for Claude, Cursor and Devin, SQL notebooks and visual EXPLAIN.

01Result

TabularisDB/tabularis ↗

TabularisDB/tabularis AI coding statistics: 2.7%

of 1,607 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.7% agent · top contributor 37.2%13 contributors
org-wide

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

43
agent commits
1,564
other considered commits
13
agent contributors
37.2%
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

43assisted
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
2026-021.4%289
2026-034.4%248
2026-041.9%208
2026-054%125
2026-060.8%125
2026-073%234
2026-080.4%279
2026-0910.1%99

Peak month: 10.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic311.9%
Cursor AgentAnysphere80.5%
GitHub CopilotGitHub30.2%
Gemini CLIGoogle10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 3f0780e1 on GitHubtest(postgres): regenerate golden files for table and column commentsClaude Code
  • 05df3f99 on GitHubfix(dump): escape JSON columns and backslashes per dialectClaude Code
  • 370f4d7c on GitHubfix(snap): ship a desktop entry so the app appears in the launcherClaude Code
  • 74faeead on GitHubfix: stop SSH tunnels on proxy config save instead of orphaning themCursor Agent
  • a9d02987 on GitHubfix: address proxy PR review (blocker + notes + registry proxy)Cursor Agent
  • f5dc6373 on GitHubfix: route Tabularium SDK HTTP through app_http proxyCursor Agent
  • b1b085c3 on GitHubAdd cloudflare d1 http plugin (#430)GitHub Copilot
  • 1c54d97b on GitHubfeat(editor):add configurable shortcut to force IntelliSense suggestions (GitHub Copilot
  • b015b350 on GitHubfix(DataGrid): handle empty column names from driversGitHub Copilot
  • d6339a5d on GitHubSupport for ssh authentication with security keys (like Yubikey) (#262)Gemini CLI

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 window2,023
Merge commits removed−389
CI / dependency bots removed−27
Considered1,607

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 TabularisDB/tabularis

Scan another repository

Try