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 free, open-source Obsidian plugin that makes your vault smarter: better search, an interactive knowledge graph, and an AI assistant that knows your notes.

01Result

s2b-dev/smart-second-brain ↗

s2b-dev/smart-second-brain AI coding statistics: 3.1%

of 541 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.1% agent · top contributor 70.6%3 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

17
agent commits
524
other considered commits
3
agent contributors
70.6%
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

17assisted
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
2026-020%7
2026-031.2%84
2026-047.4%27
2026-050%29
2026-060%3
2026-071.3%76
2026-080%208
2026-0912.1%107

Peak month: 12.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic142.6%
GitHub CopilotGitHub30.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • baa4ee82 on GitHubrelease: 2.1.2Claude Code
  • 915fe68e on GitHubperf(chat): render the streaming reply incrementally instead of re-parsingClaude Code
  • 24ba979b on GitHubci(release): update an existing release's assets instead of failing, skip Claude Code
  • c7a7830c on GitHubfeat: implement space management features including creation, immersion, aGitHub Copilot
  • e6c7fdd9 on GitHubfix: update baseline-browser-mapping version and remove unused dependencieGitHub Copilot
  • a1760573 on GitHubfeat: implement inline diff view and processing for pending changes (#262)GitHub Copilot

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 window542
Merge commits removed−1
CI / dependency bots removed−0
Considered541

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 →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 s2b-dev/smart-second-brain

Scan another repository

Try