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.

TypeScript ETL toolkit for indexing Ethereum, Solana, and Substrate data, sourced from SQD Network.

01Result

subsquid/squid-sdk ↗

subsquid/squid-sdk AI coding statistics: 31.2%

of 365 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

31.2% agent · top contributor 76.3%9 contributors

team

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

114

agent commits

251

other considered commits

agent contributors

76.3%

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

114assisted

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

Peak month: 76%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	112	30.7%
GitHub Copilot	GitHub	2	0.5%
OpenAI Codex	OpenAI	1	0.3%

03Evidence

Inspect the matches

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

Matched commit samples

7d98829e on GitHubci(docker): publish the raw-archive-recompress imageClaude Code
bb038e68 on GitHubfeat(archive-layout): zstd long-distance matching with a 128 MiB windowClaude Code
3f55dd78 on GitHubfeat(archive-layout): read and write zstd data chunksClaude Code
e33df261 on GitHubapply suggestions from code reviewGitHub Copilot
41ff2287 on GitHubopenreader: allow to configure transaction serialization levelGitHub Copilot
05b08775 on GitHubfix(evm): reject unmappable debug call frames before they are archivedOpenAI 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	407
Merge commits removed	−42
CI / dependency bots removed	−0
Considered	365

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 subsquid/squid-sdk

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	27
2026-03	5.4%	56
2026-04	7.5%	67
2026-05	4.8%	42
2026-06	8.3%	24
2026-07	76%	125
2026-08	33.3%	9
2026-09	26.7%	15