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.

Core engine for the Brave browser for mobile and desktop. For issues https://github.com/brave/brave-browser/issues

01Result

brave/brave-core ↗

brave/brave-core AI coding statistics: 0.4%

of 6,896 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
0.4% agent · top contributor 35.7%9 contributors
org-wide

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

28
agent commits
6,868
other considered commits
9
agent contributors
35.7%
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

28assisted
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
2026-010%1
2026-020%805
2026-030.5%821
2026-040.1%1011
2026-050.6%832
2026-060.8%918
2026-070.5%1024
2026-080.5%922
2026-090.2%562

Peak month: 0.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic160.2%
Cursor AgentAnysphere80.1%
GitHub CopilotGitHub40.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • c1e07a17 on GitHub[shortcuts]: Allow removing default shortcuts on macOS (#37951)Claude Code
  • f06f552e on GitHub[Android] Fix Search in Settings tests for hidden Developer options (#3834Claude Code
  • 127382ec on GitHubTreat sandboxed .onion pages as .onion for insecure forms (#37988)Claude Code
  • 80ac86c5 on GitHubUse custom theme colors in welcome preview (#39424)Cursor Agent
  • 3d2e2a7a on GitHubUpdate Customize NTP dialog design (#38621)Cursor Agent
  • bf27250a on GitHubPreset focus to "Done" button when typing in new profile name field (#3814Cursor Agent
  • 130f0d6d on GitHubAvoid tinting tabs for achromatic user colors (#39675)GitHub Copilot
  • 99a94916 on GitHubUpdate design for Tool permission prompt in Leo (#39230)GitHub Copilot
  • 1be1cee5 on GitHubAlign ultra-dark tab-strip control icons with toolbar colors (#38536)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 window6,958
Merge commits removed−40
CI / dependency bots removed−22
Considered6,896

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 brave/brave-core

Scan another repository

Try