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 robust, high-performance execution client for Ethereum node operators.

01Result

NethermindEth/nethermind ↗

NethermindEth/nethermind AI coding statistics: 28.3%

of 1,739 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
28.3% agent · top contributor 26.4%57 contributors
org-wide

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

492
agent commits
1,247
other considered commits
57
agent contributors
26.4%
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

490assisted
2autonomous

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
2026-0223.2%138
2026-0325%204
2026-0431.3%211
2026-0534.7%262
2026-0635.7%221
2026-0730.9%301
2026-0828.6%175
2026-0913.2%227

Peak month: 35.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic45826.3%
GitHub CopilotGitHub492.8%
Cursor AgentAnysphere50.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • e8babde2 on GitHubci: bound and spread the GCP sync-runner fleet, and put master validation Claude Code
  • fea2e60f on GitHubfix(xdc): verify a SyncInfo's QC and TC independently, and relay it (#1329Claude Code
  • 458b9192 on GitHubfeat(xdc): reject transactions under the minimum gas price on pool admissiClaude Code
  • 4b0d9a29 on GitHubperf(rpc): cut eth_call overhead in memory, code stream, and tx parse (#12GitHub Copilot
  • 3fbc3235 on GitHubfix(era): advance finality during replay (#12423)GitHub Copilot
  • e5ff8d1c on GitHubfeat: add `proof_getProofWithMeta` JSON-RPC method (#11498)GitHub Copilot
  • 10b1275f on GitHubxdc eth endpoints (#11939)Cursor Agent
  • f0243f6c on GitHubfix(tracing): synthesize root action in ParityLikeTxTracer.MarkAsSuccess (Cursor Agent
  • cd907370 on GitHubrefactor(aura): isolate AuRa concerns inside the AuRa plugin (#11938)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 window1,818
Merge commits removed−1
CI / dependency bots removed−78
Considered1,739

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 →C# AI coding statisticsCompare evidence across C# 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 NethermindEth/nethermind

Scan another repository

Try