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.

Optimism is Ethereum, scaled.

01Result

ethereum-optimism/optimism ↗

ethereum-optimism/optimism AI coding statistics: 39.2%

of 1,925 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

39.2% agent · top contributor 21.6%39 contributors

org-wide

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

754

agent commits

1,171

other considered commits

agent contributors

21.6%

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

582assisted

172autonomous

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: 55%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	728	37.8%
GitHub Copilot	GitHub	15	0.8%
Devin	Cognition	9	0.5%
OpenAI Codex	OpenAI	4	0.2%

03Evidence

Inspect the matches

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

Matched commit samples

3cdd9f23 on GitHubdocs: add preconfirmation architecture transition notice (#22843)Claude Code
a74e0eba on GitHubdocs: pin component versions and dates for Upgrade 20 (#22865)Claude Code
6945cd72 on GitHubcontracts-bedrock: git-ignore foundry.lock (#22853)Claude Code
9c38f588 on GitHubdocs: Update op-reth-historical-proof-config.mdx (#20846)GitHub Copilot
681867a2 on GitHubchore(rust/op-reth): port historical proofs binary change (#19252)GitHub Copilot
f67fd6c6 on GitHubRemove accidental `PR.md` from repository root (#19497)GitHub Copilot
348e1291 on GitHubtest(contracts): improve LegacyMintableERC20 test coverage and quality (#1Devin
7d513f71 on GitHubtest(contracts): improve ETHLiquidity test coverage (#19665)Devin
81e3673f on GitHubchore(contracts-bedrock): replace pre-pr with pr (check-fast) in CI and juDevin
4f196aad on GitHubci: skip merge queue test suites for docs-only changes (#22434)OpenAI Codex
00c3d3ee on GitHubdocs: migrate flashblocks -> subblocks (#22417)OpenAI Codex
75a56602 on GitHubop-reth: add subblocks CLI flag aliases (#22431)OpenAI Codex

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	1,967
Merge commits removed	−5
CI / dependency bots removed	−37
Considered	1,925

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 →Devin commitsBrowse repositories with detected Devin signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Go AI coding statisticsCompare evidence across Go 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 ethereum-optimism/optimism

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	11.8%	288
2026-03	55%	258
2026-04	46.6%	266
2026-05	27.6%	286
2026-06	44.1%	222
2026-07	53.4%	324
2026-08	41.8%	201
2026-09	25%	80