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.

Multiplayer top-down shooter made from scratch in C++. Web version: https://play.hypersomnia.io Made in 🇵🇱

01Result

TeamHypersomnia/Hypersomnia ↗

TeamHypersomnia/Hypersomnia AI coding statistics: 29.6%

of 423 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
29.6% agent · top contributor 67.2%3 contributors
individual

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

125
agent commits
298
other considered commits
3
agent contributors
67.2%
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

41assisted
84autonomous

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
2026-0247.6%42
2026-0349.6%121
2026-0415.7%51
2026-057.7%142
2026-0619%21
2026-080%2
2026-0950%44

Peak month: 50%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub9322%
Claude CodeAnthropic327.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 6b908c11 on GitHubCheck all 4 cell corners for cover in find_closest_coverGitHub Copilot
  • aa4c16cb on GitHubGate danger-avoidance dash behind speed > 500 px/sGitHub Copilot
  • fc8566d2 on GitHubDynamic cover search radius based on explosion effective_radiusGitHub Copilot
  • e64be40c on GitHubknockout indicators: weapon and circumstance icons as orange silhouettesClaude Code
  • 26324f71 on GitHubdont leak zoom-out LINEAR filtering into GUI passesClaude Code
  • d510179d on GitHubquarter-pixel bias in GUI projections to keep NEAREST sampling off texel eClaude Code

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 window423
Merge commits removed−0
CI / dependency bots removed−0
Considered423

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 →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 TeamHypersomnia/Hypersomnia

Scan another repository

Try