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.

Leantime is a goals focused project management system for non-project managers. Building with ADHD, Autism, and dyslexia in mind.

01Result

Leantime/leantime ↗

Leantime/leantime AI coding statistics: 70.5%

of 427 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
70.5% agent · top contributor 64.1%9 contributors
team

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

301
agent commits
126
other considered commits
9
agent contributors
64.1%
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

297assisted
4autonomous

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
2026-0224.6%65
2026-030%18
2026-0447.8%23
2026-0589%127
2026-0693.6%78
2026-0774.7%87
2026-08100%15
2026-0957.1%14

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic29569.1%
GitHub CopilotGitHub81.9%

03Evidence

Inspect the matches

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

Matched commit samples

  • 056835f1 on GitHubchore(plugins): bump the submodule to main for 3.10.0 (#3775)Claude Code
  • 21a9b4ab on GitHubfix(components): escape statTile's `sub` by default, opt into markup via HClaude Code
  • 4b910b9c on GitHubfix(routing): resolve plugin controllers whose folder has an inner capitalClaude Code
  • 248d5e96 on GitHubfix(sessions): isolate sessions into their own redis database (#3604)GitHub Copilot
  • 5412c7ea on GitHubchore(ratelimit): raise the default API limit from 10 to 120 req/min (#359GitHub Copilot
  • 370ccba1 on GitHubfix: define $groupId variable before Blade component render in kanban viewGitHub 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 window537
Merge commits removed−95
CI / dependency bots removed−15
Considered427

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 →PHP AI coding statisticsCompare evidence across PHP 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 Leantime/leantime

Scan another repository

Try