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.

Cross Platform Terminal UI toolkit for .NET

01Result

tui-cs/Terminal.Gui ↗

tui-cs/Terminal.Gui AI coding statistics: 69.6%

of 812 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
69.6% agent · top contributor 40.7%9 contributors
org-wide

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

565
agent commits
247
other considered commits
9
agent contributors
40.7%
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

433assisted
132autonomous

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
2026-010%2
2026-0252.4%84
2026-0344.2%86
2026-0467.5%114
2026-0584.7%372
2026-0672.7%99
2026-0772.7%11
2026-0819.2%26
2026-0933.3%18

Peak month: 84.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub44254.4%
Claude CodeAnthropic14317.6%
Cursor AgentAnysphere50.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 8c9b818d on GitHubFIXES #4367 - BREAKING CHANGE - Remove legacy ConfigurationManager after MGitHub Copilot
  • 6103007e on GitHubDocument cancellation state and pin in-flight Remove contractGitHub Copilot
  • 48efa0c5 on GitHubFixes #5639. Harden TextView text synchronization (#5645)GitHub Copilot
  • 8c9b818d on GitHubFIXES #4367 - BREAKING CHANGE - Remove legacy ConfigurationManager after MClaude Code
  • c8a3ead6 on GitHubRaise Added outside the occurrence-completion finallyClaude Code
  • d46b915d on GitHubFix Tab order and reformat-on-keystroke in NumericUpDown editable modeClaude Code
  • b2b26ae7 on GitHubFixes #5635. Hide active popover on DeRegister to clear stale cells (#5657Cursor Agent
  • 907f5186 on GitHubFixes NativeAOT IL2026 in RuneJsonConverter. (#5659)Cursor Agent
  • 2e5c2dde on GitHubDocs: 2.5.0 CM/MEC leftovers for #5630 (#5658)Cursor 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 window1,251
Merge commits removed−376
CI / dependency bots removed−63
Considered812

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 →C# AI coding statisticsCompare evidence across C# 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 tui-cs/Terminal.Gui

Scan another repository

Try