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.

Autonomous AI development loop for Claude Code with intelligent exit detection

frankbria/ralph-claude-code ↗

frankbria/ralph-claude-code AI coding statistics: 27.1%

of 133 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
27.1% agent · top contributor 61.1%7 contributors
team

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

36
agent commits
97
other considered commits
7
agent contributors
61.1%
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

36assisted
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
2026-0241.4%70
2026-038.3%12
2026-040%12
2026-0566.7%9
2026-060%26
2026-070%4

Peak month: 66.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic3627.1%

Inspect the matches

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

Matched commit samples

  • 36e8b158 on GitHubfeat(enable): add --limit flag to cap issues imported from beads/GitHub (#Claude Code
  • 6e2e194d on GitHubfeat(live): show tool call details in streaming output (#253)Claude Code
  • 8c562dc4 on GitHubfix(analyzer): treat compound-command denials as non-fatal advisory (#243)Claude Code

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 window154
Merge commits removed−19
CI / dependency bots removed−2
Considered133

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 frankbria/ralph-claude-code

Scan another repository