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.

A based rollup protocol for Ethereum🥁

01Result

taikoxyz/taiko-mono ↗

taikoxyz/taiko-mono AI coding statistics: 30.1%

of 459 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
30.1% agent · top contributor 52.9%10 contributors
team

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

138
agent commits
321
other considered commits
10
agent contributors
52.9%
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

138assisted
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
2026-025.3%95
2026-035.9%68
2026-0421.4%56
2026-0525.4%59
2026-0643.5%62
2026-0756.3%71
2026-0872.2%36
2026-0975%12

Peak month: 75%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic13729.8%
Cursor AgentAnysphere40.9%
OpenAI CodexOpenAI40.9%

03Evidence

Inspect the matches

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

Matched commit samples

  • e9c9417b on GitHubfix(repo): repair the release-please lockfile jsonpaths (#22121)Claude Code
  • 15810fd0 on GitHubfeat(protocol): Proposal0023 upgrades the L1 and L2 bridges and ERC20 vaulClaude Code
  • 62bd5eea on GitHubdocs(protocol): record the Hoodi bridge and ERC20 vault upgrade of `ProposClaude Code
  • ca16fba3 on GitHubchore(protocol): record the v3.0.0 merge ancestry lost by squashing #21922Cursor Agent
  • bcba1ff1 on GitHubchore(protocol): merge taiko-alethia-protocol-v3.0.0 back to main (realignCursor Agent
  • bc3fcf1c on GitHubfeat(protocol): add optional SGX quote-freshness gate (bound quote age) (#Cursor Agent
  • ca16fba3 on GitHubchore(protocol): record the v3.0.0 merge ancestry lost by squashing #21922OpenAI Codex
  • bcba1ff1 on GitHubchore(protocol): merge taiko-alethia-protocol-v3.0.0 back to main (realignOpenAI Codex
  • bc3fcf1c on GitHubfeat(protocol): add optional SGX quote-freshness gate (bound quote age) (#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 window485
Merge commits removed−3
CI / dependency bots removed−23
Considered459

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Rust AI coding statisticsCompare evidence across Rust 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 taikoxyz/taiko-mono

Scan another repository

Try