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.

Build, run and scale AI agents like API and microservices

01Result

Agent-Field/agentfield ↗

Agent-Field/agentfield AI coding statistics: 55%

of 551 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
55% agent · top contributor 76.6%28 contributors
team

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

303
agent commits
248
other considered commits
28
agent contributors
76.6%
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

302assisted
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
2026-0266.7%18
2026-0361.8%68
2026-0434.7%118
2026-0557.1%42
2026-0624.6%57
2026-0776.7%90
2026-0866.4%146
2026-0933.3%12

Peak month: 76.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic29854.1%
Cursor AgentAnysphere101.8%
GitHub CopilotGitHub10.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • d2fad283 on GitHubchore(deps): bump @ai-sdk/provider-utils from 4.0.23 to 4.0.50 in /desktopClaude Code
  • 78215f17 on GitHubfix(storage): workflow reaper consults execution activity clock (#1046)Claude Code
  • 366c7ff1 on GitHubfix(telemetry): report each terminal outcome once and stamp usage_context Claude Code
  • 366c7ff1 on GitHubfix(telemetry): report each terminal outcome once and stamp usage_context Cursor Agent
  • 02416e69 on GitHubfix(control-plane): honor AGENTFIELD_LOG_LEVEL in the af binary, stop doubCursor Agent
  • 88793e8d on GitHubfix(sdk/go,sdk/typescript): refuse OpenRouter audio formats that cannot woCursor Agent
  • 99f3e9f8 on GitHubfix(sdk/go): rewrite max_tokens to max_completion_tokens for newer OpenAI GitHub 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 window1,179
Merge commits removed−72
CI / dependency bots removed−556
Considered551

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 →Go AI coding statisticsCompare evidence across Go 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 Agent-Field/agentfield

Scan another repository

Try