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.

Open-source Reflect rewrite: A local-first AI agent-friendly Markdown note-taking app

01Result

team-reflect/reflect-open ↗

team-reflect/reflect-open AI coding statistics: 36.1%

of 846 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
36.1% agent · top contributor 99.3%3 contributors
individual

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

305
agent commits
541
other considered commits
3
agent contributors
99.3%
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

305assisted
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
2026-0647.8%383
2026-0734.2%319
2026-0812%92
2026-093.8%52

Peak month: 47.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic30335.8%
Cursor AgentAnysphere50.6%
GitHub CopilotGitHub20.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1fcc0b3d on GitHubfix: stop the iCloud metadata query from pinning fileproviderd on macOS (#Claude Code
  • debfeaa3 on GitHubdocs: explain the benign BRItemCollectionGatherer watch faults from sync-eClaude Code
  • e83cd86a on GitHubfix(desktop): eliminate white flash on window startup (#882)Claude Code
  • c1138c3a on GitHubEditor: V1-style markers, reading size, and a text-size setting (#368)Cursor Agent
  • 6aa2f6cd on GitHubfix(desktop): keep "All notes" selected while editing a named note (#365)Cursor Agent
  • 496ccbca on GitHubRelease v0.2.1 (#361)Cursor Agent
  • 0c9d2eb1 on GitHubfix: improve iOS note deletion (#1192)GitHub Copilot
  • cc5e3eba on GitHubfix: reduce battery drain from mobile scrolling and idle polling (#962)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 window1,047
Merge commits removed−22
CI / dependency bots removed−179
Considered846

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 team-reflect/reflect-open

Scan another repository

Try