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.

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

study8677/repobrain ↗

study8677/repobrain AI coding statistics: 41%

of 188 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
41% agent · top contributor 94.8%4 contributors
individual

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

77
agent commits
111
other considered commits
4
agent contributors
94.8%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

77assisted
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
2026-0210%10
2026-0338.1%42
2026-0447.2%72
2026-0570.6%17
2026-0644.4%9
2026-0742.9%14
2026-0828.6%14
2026-090%10

Peak month: 70.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic7338.8%
Cursor AgentAnysphere42.1%

Inspect the matches

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

Matched commit samples

  • 46d4b309 on GitHubAdd freshness-aware ask, incremental quick refresh, rb doctor, and README Claude Code
  • b5024511 on GitHubBump product version to 0.3.0 and CLI to 2.0.0 for RepoBrain releaseClaude Code
  • cab5a7d7 on GitHubRename functional identifiers from Antigravity to RepoBrainClaude Code
  • aefb94d1 on GitHubdocs: fix documentation inaccuracies flagged by Codex in PR #115 (#117)Cursor Agent
  • f32cb113 on GitHubdocs: update hub/ layout in READMEs to match actual files (#116)Cursor Agent
  • a1de58b1 on GitHubdocs: update documentation to match current codebase (2026-08) (#115)Cursor Agent

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 window238
Merge commits removed−49
CI / dependency bots removed−1
Considered188

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 study8677/repobrain

Scan another repository