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.

Ethereum implementation on the efficiency frontier

01Result

erigontech/erigon ↗

erigontech/erigon AI coding statistics: 20.8%

of 2,605 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
20.8% agent · top contributor 31.4%28 contributors
org-wide

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

541
agent commits
2,064
other considered commits
28
agent contributors
31.4%
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

536assisted
5autonomous

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
2026-0213.1%382
2026-0346.4%343
2026-0441.3%320
2026-0535.8%285
2026-0617.7%265
2026-076.8%439
2026-084.3%370
2026-092.5%201

Peak month: 46.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic49819.1%
GitHub CopilotGitHub552.1%
OpenAI CodexOpenAI10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 6ac59753 on GitHubdocs(site): drop the v3.5 pruning migration note (#23345)Claude Code
  • d364937d on GitHubdocs(site): forward-port version resolution and retarget docs automation (Claude Code
  • 9350b155 on GitHubdocs: add a security policy and fix the reporting instructions (#23168)Claude Code
  • 93157018 on GitHubexecution/protocol, execution/types: validate access list and blob rules iGitHub Copilot
  • 7ab9d2a4 on GitHubjustfile: switch Windows cross-build uTP tag to `purego_utp` (#23906)GitHub Copilot
  • b7aef006 on GitHublru: accounting per-key overhead (#23552)GitHub Copilot
  • 9f42f012 on GitHubAdded SSZ REST for Engine API (#21203)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 window2,721
Merge commits removed−0
CI / dependency bots removed−116
Considered2,605

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 →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 erigontech/erigon

Scan another repository

Try