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, self-hosted AI code review. Bring your own LLM.

01Result

kodustech/kodus-ai ↗

kodustech/kodus-ai AI coding statistics: 47.3%

of 3,262 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

47.3% agent · top contributor 56.2%12 contributors

team

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

1,544

agent commits

1,718

other considered commits

agent contributors

56.2%

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

1544assisted

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: 62.5%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	1538	47.1%
GitHub Copilot	GitHub	4	0.1%
Cursor Agent	Anysphere	2	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

b734c202 on GitHubchore(pr-template): keep eval evidence inside the 1000-char budgetClaude Code
7491608a on GitHubchore(issues): keep the needs-approval gate on the work item templateClaude Code
7932c7ff on GitHubfix(web): the star count linked to a page GitHub no longer servesClaude Code
86a11301 on GitHubPotential fix for pull request finding 'CodeQL / Incomplete string escapinGitHub Copilot
c180aadf on GitHubkody fixGitHub Copilot
618049c7 on GitHubupdate uiGitHub Copilot
9e2cb087 on GitHubfix(centralized-config): plain-ify rule payloads before yaml.dumpCursor Agent
b7e62980 on GitHubAdd context to language selector: clarify it's for Kody LanguageCursor 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	4,215
Merge commits removed	−948
CI / dependency bots removed	−5
Considered	3,262

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 kodustech/kodus-ai

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	17.4%	270
2026-03	33.9%	437
2026-04	62.5%	424
2026-05	61.5%	452
2026-06	57.3%	321
2026-07	56.1%	433
2026-08	34.7%	516
2026-09	48.9%	409