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.

Communicate with an LLM provider using a single interface

01Result

mozilla-ai/any-llm ↗

mozilla-ai/any-llm AI coding statistics: 49.1%

of 320 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
49.1% agent · top contributor 61.1%31 contributors
team

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

157
agent commits
163
other considered commits
31
agent contributors
61.1%
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

156assisted
1autonomous

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
2026-0240.3%67
2026-0372%50
2026-0461.9%21
2026-0515.4%26
2026-0640%30
2026-0733.3%21
2026-0870.4%71
2026-0923.5%34

Peak month: 72%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic14846.3%
Cursor AgentAnysphere92.8%
GitHub CopilotGitHub10.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • bcfdbe02 on GitHubfeat(usage): preserve provider cache meter details (#1335)Claude Code
  • 12ee61ce on GitHubfix(ci): gate labeled integration tests while testing PR head (#1341)Claude Code
  • f4451627 on GitHubchore: scope test retries to integration tests and port agent guidance froClaude Code
  • 15fbfdfc on GitHubfix(xai): map the provider finish reason instead of hardcoding stop (#1353Cursor Agent
  • 909d26e6 on GitHubfix(gemini): map tool_choice none and the named-function form (#1352)Cursor Agent
  • e822b281 on GitHubfix(providers): preserve typed safety refusals (#1328)Cursor Agent
  • e99f7a17 on GitHubfix(otari): preserve cache_control via native /messages pass-through (#112GitHub Copilot

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 window357
Merge commits removed−0
CI / dependency bots removed−37
Considered320

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 →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 mozilla-ai/any-llm

Scan another repository

Try