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.

Design principles for agent ergonomics. Higher accuracy with lower token cost than both MCP and regular CLI.

01Result

kunchenguid/axi ↗

kunchenguid/axi AI coding statistics: 13%

of 138 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

13% agent · top contributor 22.2%9 contributors

org-wide

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

agent commits

120

other considered commits

agent contributors

22.2%

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

18assisted

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: 41.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	13	9.4%
Cursor Agent	Anysphere	5	3.6%

03Evidence

Inspect the matches

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

Matched commit samples

5c1990d3 on GitHubfeat(catalog): add basecamp-axi community entry (#192)Claude Code
7626619a on GitHubdocs(catalog): add calcom-axi (#190)Claude Code
7bfcf42b on GitHubdocs(catalog): add coolify-axi to the community catalog (#178)Claude Code
99966131 on GitHubdocs(catalog): add ha-axi to the community catalog (#187)Cursor Agent
787d7747 on GitHubdocs(catalog): describe doctl-axi by the DigitalOcean resources it managesCursor Agent
470b20c0 on GitHubdocs: add porkbun-axi to the community catalog (#181)Cursor 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	150
Merge commits removed	−1
CI / dependency bots removed	−11
Considered	138

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 kunchenguid/axi

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	0%	32
2026-04	0%	11
2026-05	0%	4
2026-06	7.1%	14
2026-07	15.4%	26
2026-08	17.6%	34
2026-09	41.2%	17