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.

Rapid Application Development (RAD) Environment for Autodesk Revit®

01Result

pyrevitlabs/pyRevit ↗

pyrevitlabs/pyRevit AI coding statistics: 19.4%

of 1,276 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
19.4% agent · top contributor 26.6%22 contributors
org-wide

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

248
agent commits
1,028
other considered commits
22
agent contributors
26.6%
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

188assisted
60autonomous

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
2026-0217.3%208
2026-037.1%112
2026-047.9%178
2026-0530.5%167
2026-0626.2%195
2026-0735.4%127
2026-0815.2%178
2026-0914.4%111

Peak month: 35.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub14511.4%
Claude CodeAnthropic544.2%
Cursor AgentAnysphere514%

03Evidence

Inspect the matches

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

Matched commit samples

  • c06c6a77 on GitHubAdd explicit NUnit using to reflection compatibility testsGitHub Copilot
  • 93101cb0 on GitHubUse MissingMemberException for required reflected membersGitHub Copilot
  • 90be785f on GitHubHandle legacy runtime configs in session script setupGitHub Copilot
  • a9cde116 on GitHubfeat(keynotes): multi-project Keynote Manager, clipboard, and modeless-winClaude Code
  • 5288d052 on GitHubFix/routes reload crash (#3558)Claude Code
  • af5aa074 on GitHubfix(Keynotes): readable search box text and monochrome icons in dark themeClaude Code
  • ee13a34b on GitHubfix: make library search-path cache seed order-stableCursor Agent
  • 5447c553 on GitHubfix: put library-extension roots on command search paths and invalidate roCursor Agent
  • 40311903 on GitHubfix: put library-extension roots on startup and hook search pathsCursor Agent

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 window2,014
Merge commits removed−651
CI / dependency bots removed−87
Considered1,276

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 →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 pyrevitlabs/pyRevit

Scan another repository

Try