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.

The pretty much "official" DSPy framework for Typescript

01Result

ax-llm/ax ↗

ax-llm/ax AI coding statistics: 32%

of 775 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
32% agent · top contributor 91.1%8 contributors
individual

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

248
agent commits
527
other considered commits
8
agent contributors
91.1%
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

248assisted
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
2026-0213.7%117
2026-0314.6%82
2026-0445.5%33
2026-0513.1%84
2026-0666.3%178
2026-0736.4%173
2026-0814%93
2026-090%15

Peak month: 66.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic24231.2%
Cursor AgentAnysphere60.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • d623f03d on GitHubfix(gemini): route an effort level to thinkingLevel, not thinkingBudget (#Claude Code
  • 08d396d9 on GitHubfix(gemini): send the thinking config the port never built (#620)Claude Code
  • c4851c89 on GitHubfix(go): surface HTTP errors from embed, transcribe and speak (#615)Claude Code
  • dadcaa64 on GitHubrefactor: update RLM configuration and documentation for runtime characterCursor Agent
  • d9b5e9a2 on GitHubfeat: rename AxCodeInterpreter to AxCodeRuntimeCursor Agent
  • 6d0b314b on GitHubfix: make RLM interpreter returns less brittleCursor 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 window782
Merge commits removed−7
CI / dependency bots removed−0
Considered775

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 ax-llm/ax

Scan another repository

Try