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.

Self-hosted realtime soundscape analyser for birds, bats and other wildlife. Multi-model local AI inference, runs 24/7 on a Raspberry Pi.

01Result

tphakala/birdnet-go ↗

tphakala/birdnet-go AI coding statistics: 5.3%

of 1,837 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.3% agent · top contributor 38.1%17 contributors
org-wide

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

97
agent commits
1,740
other considered commits
17
agent contributors
38.1%
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

97assisted
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
2026-023.5%199
2026-032.1%474
2026-040.7%152
2026-053%338
2026-0611.9%337
2026-079.3%161
2026-082.2%89
2026-0913.8%87

Peak month: 13.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic884.8%
Cursor AgentAnysphere60.3%
GitHub CopilotGitHub30.2%
Gemini CLIGoogle20.1%
OpenAI CodexOpenAI10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 32e1f50a on GitHubfeat(media): audible bats mode for bat detection playback (#3743)Claude Code
  • a8a3047a on GitHubfix(analytics): report the real first-heard time in the daily species summClaude Code
  • 94dfe6e9 on GitHubfix(audiocore): bound FFmpeg stderr capture to a trailing 64 KiB window (#Claude Code
  • f3b2eeed on GitHubfix(search): match partial common names (#4040)Cursor Agent
  • a4a57e22 on GitHubfix(conf): silence spurious cgroup error on non-Linux platforms (#3193)Cursor Agent
  • afe6b3fd on GitHubfix(taskfile): correct architecture detection and cleanup setup-dev (#3192Cursor Agent
  • 32e1f50a on GitHubfeat(media): audible bats mode for bat detection playback (#3743)GitHub Copilot
  • 570877a9 on GitHubfeat(species): add infrequent species tracking category (#3791)GitHub Copilot
  • 3a1968ad on GitHubfeat(realtime): add "enabled" toggle for audio streams (#2836)GitHub Copilot
  • f21d07cf on GitHubfeat: Openvino GPU offload compatibility for Intel iGPU (#3888)Gemini CLI
  • d3b2db6e on GitHubrefactor(datastore): deduplicate database stats queries and fix TOCTOU racGemini CLI
  • 363bf7b5 on GitHubfix(range): preserve native scores for included species (#3976)OpenAI Codex

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 window2,021
Merge commits removed−61
CI / dependency bots removed−123
Considered1,837

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 tphakala/birdnet-go

Scan another repository

Try