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.

Official TestSprite CLI — AI-powered automated testing from your terminal

01Result

TestSprite/testsprite-cli ↗

TestSprite/testsprite-cli AI coding statistics: 9.7%

of 113 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
9.7% agent · top contributor 27.3%5 contributors
team

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

11
agent commits
102
other considered commits
5
agent contributors
27.3%
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

11assisted
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
2026-066.3%16
2026-079.8%82
2026-089.1%11
2026-0925%4

Peak month: 25%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic87.1%
Cursor AgentAnysphere32.7%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1de8f53f on GitHubdocs: replace the expired Discord invite with a permanent one (#337)Claude Code
  • d2f0357e on GitHubfix(ci): migrate github-script to v8 — repair the repo-wide broken gate chClaude Code
  • 93c621c6 on GitHubfix(rerun): reject explicit IDs with --all and --status/--skip-terminal wiClaude Code
  • cdef654d on GitHubfix(rerun): emit partial stdout on TimeoutError in single-FE rerun --wait Cursor Agent
  • 108a9131 on GitHubfix(batch): classify RequestTimeoutError as timeout in --all --wait fan-ouCursor Agent
  • 3fd703ff on GitHubfix(poll): emit partial run to stdout on TimeoutError in run --wait and teCursor Agent

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 window120
Merge commits removed−5
CI / dependency bots removed−2
Considered113

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 TestSprite/testsprite-cli

Scan another repository

Try