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.

Real-time monitoring, slowlog analysis, and audit trails for Valkey and Redis

01Result

BetterDB-inc/monitor ↗

BetterDB-inc/monitor AI coding statistics: 10%

of 542 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

10% agent · top contributor 64.8%2 contributors

individual

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

agent commits

488

other considered commits

agent contributors

64.8%

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

54assisted

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

Peak month: 23.4%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	51	9.4%
Cursor Agent	Anysphere	5	0.9%

03Evidence

Inspect the matches

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

Matched commit samples

33712b94 on GitHubfeat(anomaly): ghost-membership detector for CLUSTER RESET stale ids (#175Claude Code
a5468a06 on GitHubchore(release): monitor 0.33.0Claude Code
af87a84d on GitHubfeat(anomaly): detect replicas stuck in slot migrating/importing state (vaClaude Code
9e6004ec on GitHubdocs: refresh README and fix production endpoint paths (#365)Cursor Agent
26679f21 on GitHubAgent cache py (#117)Cursor Agent
73ca5699 on GitHubAdd @betterdb/agent-cache package — multi-tier LLM/tool/session cache withCursor 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 window	588
Merge commits removed	−12
CI / dependency bots removed	−34
Considered	542

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 →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 BetterDB-inc/monitor

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	90
2026-03	23.4%	47
2026-04	12.1%	58
2026-05	7%	86
2026-06	14.1%	71
2026-07	19.4%	93
2026-08	2.6%	77
2026-09	0%	20