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 lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs in the web browser, on the desktop, on mobile, and inside Jupyter notebooks.

01Result

opengeos/GeoLibre ↗

opengeos/GeoLibre AI coding statistics: 1.9%

of 1,400 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.9% agent · top contributor 22.2%16 contributors
org-wide

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

27
agent commits
1,373
other considered commits
16
agent contributors
22.2%
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

27assisted
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
2026-053.8%78
2026-060.4%504
2026-072.5%326
2026-082.5%358
2026-093.7%134

Peak month: 3.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic201.4%
Cursor AgentAnysphere50.4%
GitHub CopilotGitHub30.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 737f9de6 on GitHubfeat: add getLayers/onLayersChanged to GeoLibreAppAPI (#2386)Claude Code
  • 638392ad on GitHubfix(i18n): settle Italian terminology, starting with "layer" (#2341)Claude Code
  • c63f6e2d on GitHubfix(i18n): tidy up the Spanish catalog (#2340)Claude Code
  • 1a35006b on GitHubfix(map): allow grabbing the map during inertial pan (#1961)Cursor Agent
  • 851bddbc on GitHubfix(style): auto-fill proportional size range and show it in print legend Cursor Agent
  • 11626873 on GitHubSync GeoEditor drawings to a single Sketches layer (#77) (#79)Cursor Agent
  • 0b6a4051 on GitHubfix: install MapLibre transform compat on the headless entry (#2088)GitHub Copilot
  • 838ee4f8 on GitHubfix: use safe fallback for crypto.randomUUID in non-secure contexts (#115)GitHub Copilot
  • 11626873 on GitHubSync GeoEditor drawings to a single Sketches layer (#77) (#79)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 window1,461
Merge commits removed−0
CI / dependency bots removed−61
Considered1,400

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 opengeos/GeoLibre

Scan another repository

Try