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.

Python SQL Parser and Transpiler

01Result

tobymao/sqlglot ↗

tobymao/sqlglot AI coding statistics: 5.1%

of 1,388 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.1% agent · top contributor 9.9%36 contributors
org-wide

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

71
agent commits
1,317
other considered commits
36
agent contributors
9.9%
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

71assisted
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
2026-022.1%235
2026-033.1%256
2026-044.2%189
2026-056.5%123
2026-064.9%123
2026-075.8%190
2026-088.6%210
2026-0911.3%62

Peak month: 11.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic604.3%
GitHub CopilotGitHub50.4%
Cursor AgentAnysphere50.4%
Gemini CLIGoogle10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 4b84b4d4 on GitHubfix(fabric)!: keep scale and length for MONEY, SMALLMONEY, XML and IMAGE [Claude Code
  • 83abff65 on GitHubfix(expressions)!: render a DynamicIdentifier in Table.name [CLAUDE] (#832Claude Code
  • 1d753d72 on GitHubfix(optimizer)!: EXISTS over a scalar aggregate is always true [CLAUDE] (#Claude Code
  • eee4750c on GitHubfix(optimizer)!: preserve UNION ALL arm width when nested set op forces coGitHub Copilot
  • a51c3961 on GitHubfix(optimizer)!: week floor is off by a cycle for Sunday-start dialects (#GitHub Copilot
  • 6944a6c3 on GitHubrefactor!: Improve typing annotations for planner, schema, serde, and tranGitHub Copilot
  • bb6220b7 on GitHubfix(snowflake)!: stop dropping structured types on CREATE TABLE [GROK] (#8Cursor Agent
  • f131ec9f on GitHubfix(snowflake): parse a qualified wildcard in OBJECT_CONSTRUCT_KEEP_NULL (Cursor Agent
  • 7cca122d on GitHubfix(clickhouse): preserve quoted parameterized relations (#8198)Cursor Agent
  • 9457cf66 on GitHubfix: multiline comment idempotency in connectors [GEMINI] (#7691)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 window1,419
Merge commits removed−2
CI / dependency bots removed−29
Considered1,388

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 →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 tobymao/sqlglot

Scan another repository

Try