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.

A simple CalDAV (calendar) and CardDAV (contact) server.

01Result

Kozea/Radicale ↗

Kozea/Radicale AI coding statistics: 1.1%

of 1,013 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.1% agent · top contributor 72.7%2 contributors
individual

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

11
agent commits
1,002
other considered commits
2
agent contributors
72.7%
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
2026-020%153
2026-030%279
2026-041.4%222
2026-050%123
2026-060%56
2026-0730.4%23
2026-080.8%121
2026-090%36

Peak month: 30.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic80.8%
GitHub CopilotGitHub30.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 0e15021c on GitHubFix: time-range filter on VTODO with DTSTART/DUE and CREATED/COMPLETEDClaude Code
  • 651e3021 on GitHubFix: serve_resource/serve_folder ignore mimetypes and fallback_mimetype paClaude Code
  • f3868845 on GitHubFix: free-busy REPORT always fails when max_freebusy_occurrence is 0Claude Code
  • 42f8d5df on GitHubUI: Fix: Load username from principal componentGitHub Copilot
  • cbf1d508 on GitHubUI: Fix handling of servers with PrefixGitHub Copilot
  • 5c1e6791 on GitHubUI: (internal) rename close button to close on incoming sharesGitHub 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 window1,183
Merge commits removed−170
CI / dependency bots removed−0
Considered1,013

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 →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 Kozea/Radicale

Scan another repository

Try