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 Consensus client for the Zig and TypeScript ecosystem

ChainSafe/lodestar ↗

ChainSafe/lodestar AI coding statistics: 15.3%

of 622 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
15.3% agent · top contributor 27.4%13 contributors
org-wide

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

95
agent commits
527
other considered commits
13
agent contributors
27.4%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

95assisted
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
2026-0218.1%72
2026-0320.3%74
2026-0411.3%80
2026-0518%50
2026-069.1%55
2026-0730.8%78
2026-0812.3%130
2026-094.8%83

Peak month: 30.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic8213.2%
Gemini CLIGoogle132.1%
GitHub CopilotGitHub20.3%
OpenAI CodexOpenAI10.2%

Inspect the matches

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

Matched commit samples

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 window677
Merge commits removed−21
CI / dependency bots removed−34
Considered622

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 ChainSafe/lodestar

Scan another repository