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.

iOS & tvOS multi-emulator frontend, supporting various Atari, Bandai, NEC, Nintendo, Sega, SNK and Sony console systems… Get Started: https://wiki.provenance-emu.com |

01Result

Provenance-Emu/Provenance ↗

Provenance-Emu/Provenance AI coding statistics: 72.3%

of 2,184 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
72.3% agent · top contributor 57.6%8 contributors
team

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

1,579
agent commits
605
other considered commits
8
agent contributors
57.6%
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

1036assisted
543autonomous

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
2026-0243.8%32
2026-0373.5%1342
2026-0437.3%236
2026-0589.5%323
2026-0693.2%59
2026-0777.9%68
2026-0875.8%99
2026-0976%25

Peak month: 93.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic150268.8%
GitHub CopilotGitHub22710.4%
Cursor AgentAnysphere311.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • ca6ccfa5 on GitHubci(testflight): distribute nightlies to external groups after uploadClaude Code
  • 93f49b40 on GitHubbuild(dolphin): bump iCube to a7d9b67c08 (debug server bind + paused screeClaude Code
  • deac9576 on GitHubfix(uitesting): link VirtualJaguar dynamically to break the libchdr/zstd dClaude Code
  • ff492e12 on GitHubchore(changelog): absorb 278 pending fragment(s) (#3665)GitHub Copilot
  • 95a98ca0 on GitHubPotential fix for pull request findingGitHub Copilot
  • 16853dc8 on GitHubPotential fix for pull request findingGitHub Copilot
  • fd21b07c on GitHub[Agent] fix(cloudkit): pause heavy services during active gameplay (#3044)Cursor Agent
  • 303c0a85 on GitHubfix(wiki): anchor fragment navigation for internal wiki links (#3041)Cursor Agent
  • 77f92c4d on GitHub[Agent] fix(siri): populate search field on cold-launch Siri handoff (#303Cursor 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 window2,250
Merge commits removed−45
CI / dependency bots removed−21
Considered2,184

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 Provenance-Emu/Provenance

Scan another repository

Try